General counting |
Corpora | acl, acmtslp, alta, anlp, cath, cl, coling, conll, csal, eacl, emnlp, hlt, icassps, ijcnlp, inlg, isca, lre, lrec, ltc, mts, muc, naacl, paclic, ranlp, sem, speechc, tacl, taslp, tipster, trec |
Language | en |
Overall number of years of the history (including prediction) | 51 |
Size of past used for the prediction | 18 |
Number of occurrences of terms seen | 25351902 |
Number of different terms seen | 202832 |
Number of different simple terms seen | 40304 |
Number of terms forecasted (= number of tops) | 200 |
Algorithm and options | GaussianProcesses -L 1.0 -N 0 -K "PolyKernel -E 1.0 -C 250007" |
Tops= 200 most used terms of all times |
headword | variants | nb of occurrrences | rank |
HMM | HMMs, Hidden Markov Model, Hidden Markov Models, Hidden Markov model, Hidden Markov models, hidden Markov Model, hidden Markov Models, hidden Markov model, hidden Markov models | 134503 | 1 |
SR | ASR, ASRs, Automatic Speech Recognition, SRs, Speech Recognition, automatic speech recognition, speech recognition | 130045 | 2 |
LM | LMs, Language Model, Language Models, language model, language models | 116663 | 3 |
annotation | annotations | 105264 | 4 |
classifier | classifiers | 98151 | 5 |
POS | POSs, Part Of Speech, Part of Speech, Part-Of-Speech, Part-of-Speech, Parts Of Speech, Parts of Speech, Pos, part of speech, part-of-speech, parts of speech, parts-of-speech | 97736 | 6 |
NP | NPs, noun phrase, noun phrases | 86862 | 7 |
parser | parsers | 82789 | 8 |
segmentation | segmentations | 73112 | 9 |
SNR | SNRs, Signal Noise Ratio, Signal Noise Ratios, signal noise ratio, signal noise ratios | 69364 | 10 |
dataset | data-set, data-sets, datasets | 61751 | 11 |
GMM | GMMs, Gaussian Mixture Model, Gaussian Mixture Models, Gaussian mixture model, Gaussian mixture models | 58550 | 12 |
MT | MTs, Machine Translation, Machine Translations, machine translation, machine translations | 56610 | 13 |
neural network | ANN, ANNs, Artificial Neural Network, Artificial Neural Networks, NN, NNs, Neural Network, Neural Networks, NeuralNet, NeuralNets, neural net, neural nets, neural networks | 54672 | 14 |
iteration | iterations | 52719 | 15 |
parsing | parsings | 50762 | 16 |
SVM | SVMs, Support Vector Machine, Support Vector Machines, support vector machine, support vector machines | 50391 | 17 |
metric | metrics | 49760 | 18 |
WER | WERs, Wer, word error rate, word error rates | 47998 | 19 |
ngram | ngrams | 46227 | 20 |
subset | sub set, sub sets, sub-set, sub-sets, subsets | 45592 | 21 |
recognizer | recogniser, recognisers, recognizers | 45024 | 22 |
predicate | predicates | 43851 | 23 |
MFCC | MFCCs, Mel Frequency Cepstral Coefficient, Mel Frequency Cepstral Coefficients, Mel frequency Cepstral Coefficients, Mel frequency Cepstral coefficients, Mel-Frequency Cepstral Coefficient, mel-frequency Cepstral coefficients | 41091 | 24 |
formant | formants | 40527 | 25 |
normalization | normalisation, normalisations, normalizations | 37858 | 26 |
clustering | 37226 | 27 | |
kernel | kernels | 36279 | 28 |
covariance | covariances | 36268 | 29 |
bigram | bigrams | 36130 | 30 |
annotator | annotators | 36002 | 31 |
optimization | optimisation, optimisations, optimizations | 35254 | 32 |
dialog | dialogs | 34024 | 33 |
entropy | entropies | 33613 | 34 |
semantic | 33331 | 35 | |
gaussian | Gaussian, Gaussians, gaussians | 32276 | 36 |
WordNet | 30346 | 37 | |
derivation | derivations | 30048 | 38 |
filtering | filterings | 28623 | 39 |
codebook | codebooks | 27768 | 40 |
NLP | Natural Language Processing | 25788 | 41 |
TREC | 25453 | 42 | |
MAP | MAPs, maximum a posteriori probability | 25278 | 43 |
estimator | estimators | 25211 | 44 |
decoder | decoders | 25201 | 45 |
tagger | taggers | 25026 | 46 |
EM | EMs | 24806 | 47 |
disambiguation | disambiguations | 23951 | 48 |
syntactic | 23236 | 49 | |
spectral | 23008 | 50 | |
trigram | 3-gram, 3-grams, tri-gram, tri-grams, trigrams | 22689 | 51 |
CRF | CRFs, Conditional Random Field, Conditional Random Fields, Conditional random field, Conditional random fields | 22355 | 52 |
SMT | SMTs, Statistical Machine Translation, Statistical Machine Translations, statistical machine translation, statistical machine translations | 22078 | 53 |
waveform | waveforms | 21869 | 54 |
interpolation | interpolations | 21781 | 55 |
quantization | quantizations | 21724 | 56 |
VP | 21567 | 57 | |
coder | coders | 21558 | 58 |
Wikipedia | 21495 | 59 | |
DNN | DNNs | 21429 | 60 |
excitation | excitations | 21344 | 61 |
LDA | LDAs, Linear Discriminant Analysis | 20953 | 62 |
tweet | tweets | 20812 | 63 |
PP | PPs | 20632 | 64 |
summarization | summarisation, summarisations, summarizations | 20551 | 65 |
BLEU | 20486 | 66 | |
subband | sub-band, sub-bands, subbands | 20475 | 67 |
ontology | ontologies | 20088 | 68 |
error rate | 19617 | 69 | |
intelligibility | 19590 | 70 | |
prosody | 19553 | 71 | |
treebank | treebanks | 19549 | 72 |
preposition | prepositions | 19497 | 73 |
MLP | MLPs, multi-layer perceptron, multi-layer perceptrons, multilayer perceptron, multilayer perceptrons | 19418 | 74 |
perplexity | perplexities | 19339 | 75 |
suffix | suffixes | 19245 | 76 |
Viterbi | 19027 | 77 | |
LPC | Linear Predictive Coding | 18973 | 78 |
TTS | TTSs, Text To Speech, Text To Speech Synthesis, text to speech, text to speech synthesis, text-to-speech | 18857 | 79 |
decomposition | 18657 | 80 | |
polarity | polarities | 18512 | 81 |
acoustic | 18263 | 82 | |
bandwidth | bandwidths | 18171 | 83 |
unigram | unigrams | 18166 | 84 |
morpheme | morphemes | 18100 | 85 |
synset | synsets | 18063 | 86 |
trajectory | trajectories | 18033 | 87 |
robustness | 17992 | 88 | |
Mel | 17874 | 89 | |
coreference | coreferences | 17702 | 90 |
heuristic | heuristics | 17577 | 91 |
NE | NEs | 17519 | 92 |
modifier | modifiers | 17260 | 93 |
decoding | decodings | 17082 | 94 |
triphone | triphones | 17066 | 95 |
NIST | 16425 | 96 | |
paraphrase | paraphrases | 16337 | 97 |
cosine | cosines | 16241 | 98 |
predictor | predictors | 16082 | 99 |
mandarin | mandarins | 15989 | 100 |
punctuation | 15962 | 101 | |
spectrogram | spectrograms | 15910 | 102 |
mismatch | mismatches | 15892 | 103 |
antecedent | antecedents | 15869 | 104 |
co-occurrence | co-occurrences | 15712 | 105 |
Fourier | 15257 | 106 | |
IR | 15251 | 107 | |
subspace | subspaces | 15120 | 108 |
lexical | 14949 | 109 | |
labeling | labelings | 14805 | 110 |
LR | LRs, Language Resource, Language Resources | 14514 | 111 |
reverberation | reverberations | 14400 | 112 |
optimal | 14364 | 113 | |
posterior | posteriors | 14279 | 114 |
DT | DTs | 14273 | 115 |
collocation | collocations | 14084 | 116 |
SD | SDs | 14012 | 117 |
VQ | Vector Quantization | 13952 | 118 |
prefix | prefixes | 13869 | 119 |
MLLR | Maximum Likelihood Linear Regression | 13826 | 120 |
Thus | 13708 | 121 | |
encoding | encodings | 13489 | 122 |
DFT | DFTs, Discrete Fourier Transform | 13301 | 123 |
acoustics | 13248 | 124 | |
pruning | prunings | 13193 | 125 |
audio | audios | 13011 | 126 |
histogram | histograms | 12987 | 127 |
transducer | transducers | 12957 | 128 |
talker | talkers | 12887 | 129 |
formalism | formalisms | 12693 | 130 |
modality | modalities | 12532 | 131 |
propagation | propagations | 12495 | 132 |
FFT | 12304 | 133 | |
phonetic | 12285 | 134 | |
harmonic | harmonics | 12138 | 135 |
autocorrelation | autocorrelations | 12077 | 136 |
XML | Extensible Markup Language, XMLs | 12037 | 137 |
Timit | 12030 | 138 | |
articulation | articulations | 11961 | 139 |
WSD | Word Sense Disambiguation | 11914 | 140 |
cepstrum | cepstrums | 11777 | 141 |
UBM | universal background model | 11600 | 142 |
morphology | morphologies | 11422 | 143 |
linear | 11358 | 144 | |
temporal | 11356 | 145 | |
subtree | subtrees | 11355 | 146 |
analyzer | analyser, analysers, analyzers | 11330 | 147 |
Bayes | 11267 | 148 | |
EER | 11256 | 149 | |
residual | residuals | 11237 | 150 |
VAD | Vad, voice activity detection | 11074 | 151 |
polynomial | polynomials | 11020 | 152 |
eigenvalue | eigenvalues | 11018 | 153 |
tuple | tuples | 10884 | 154 |
concatenation | concatenations | 10854 | 155 |
www | 10794 | 156 | |
transliteration | transliterations | 10778 | 157 |
toolkit | toolkits | 10635 | 158 |
tuning | tunings | 10596 | 159 |
negation | negations | 10515 | 160 |
referent | referents | 10328 | 161 |
CL | 10257 | 162 | |
multiplication | 10204 | 163 | |
initialization | initializations | 10148 | 164 |
thesaurus | thesauri, thesauruses | 10089 | 165 |
DP | Discourse Processor | 10036 | 166 |
QA | Quality Assurance | 10025 | 167 |
schema | schemas | 9953 | 168 |
inverse | 9851 | 169 | |
RNN | RNNs, Recurrent Neural Network, Recurrent Neural Networks, recurrent neural network, recurrent neural networks | 9796 | 170 |
binary | binaries | 9674 | 171 |
subtraction | 9649 | 172 | |
grapheme | graphemes | 9610 | 173 |
indexing | indexings | 9599 | 174 |
argmax | 9571 | 175 | |
abbreviation | abbreviations | 9520 | 176 |
regularization | regularisation, regularisations, regularizations | 9450 | 177 |
dimensionality | dimensionalities | 9430 | 178 |
convolution | convolutions | 9283 | 179 |
MUC | 9281 | 180 | |
vertex | vertexes, vertices | 9237 | 181 |
quantizer | quantizers | 9215 | 182 |
test set | 9189 | 183 | |
fricative | fricatives | 9033 | 184 |
RST | 9000 | 185 | |
scaling | scalings | 8994 | 186 |
synthesizer | synthesiser, synthesisers, synthesizers | 8966 | 187 |
entailment | entailments | 8885 | 188 |
DCT | DCTs, Discrete Cosine Transform | 8857 | 189 |
codec | codecs | 8856 | 190 |
MMSE | Minimizing Mean Squared Error | 8847 | 191 |
SN | SNs | 8804 | 192 |
PCA | principle components analysis | 8801 | 193 |
beamformer | beamformers | 8783 | 194 |
FIR | 8711 | 195 | |
centroid | centroids | 8689 | 196 |
metadata | meta-data, meta-datas, meta-datum, metadatas, metadatum | 8685 | 197 |
PLP | Perceptual Linear Predictive | 8681 | 198 |
automaton | automata, automatons | 8579 | 199 |
OOV | 8503 | 200 |
Frequencies ordered by the decreasing usage over all history |
2014 | 2015 | prediction#1 | prediction#2 | prediction#3 | prediction#4 | prediction#5 | rank | |
HMM | 0.00371 | 0.00452 | 0.00387 | 0.00434 | 0.00339 | 0.00407 | 0.00350 | 1 |
SR | 0.00504 | 0.00503 | 0.00464 | 0.00496 | 0.00438 | 0.00460 | 0.00411 | 2 |
LM | 0.00484 | 0.00503 | 0.00459 | 0.00517 | 0.00435 | 0.00468 | 0.00392 | 3 |
annotation | 0.00803 | 0.00415 | 0.00571 | 0.00295 | 0.00450 | 0.00071 | 0.00225 | 4 |
classifier | 0.00467 | 0.00485 | 0.00453 | 0.00455 | 0.00387 | 0.00363 | 0.00296 | 5 |
POS | 0.00545 | 0.00438 | 0.00475 | 0.00419 | 0.00473 | 0.00376 | 0.00411 | 6 |
NP | 0.00211 | 0.00205 | 0.00170 | 0.00113 | 0.00100 | 0.00024 | 0.00029 | 7 |
parser | 0.00322 | 0.00336 | 0.00338 | 0.00344 | 0.00338 | 0.00321 | 0.00337 | 8 |
segmentation | 0.00245 | 0.00230 | 0.00225 | 0.00186 | 0.00158 | 0.00107 | 0.00089 | 9 |
SNR | 0.00283 | 0.00314 | 0.00297 | 0.00321 | 0.00289 | 0.00327 | 0.00334 | 10 |
dataset | 0.00509 | 0.00710 | 0.00733 | 0.00854 | 0.00931 | 0.01070 | 0.01181 | 11 |
GMM | 0.00343 | 0.00326 | 0.00300 | 0.00310 | 0.00235 | 0.00237 | 0.00159 | 12 |
MT | 0.00210 | 0.00268 | 0.00231 | 0.00286 | 0.00254 | 0.00300 | 0.00263 | 13 |
neural network | 0.00324 | 0.00472 | 0.00505 | 0.00628 | 0.00701 | 0.00865 | 0.00986 | 14 |
iteration | 0.00192 | 0.00220 | 0.00190 | 0.00203 | 0.00173 | 0.00183 | 0.00153 | 15 |
parsing | 0.00200 | 0.00228 | 0.00229 | 0.00243 | 0.00254 | 0.00258 | 0.00265 | 16 |
SVM | 0.00275 | 0.00252 | 0.00226 | 0.00206 | 0.00158 | 0.00126 | 0.00050 | 17 |
metric | 0.00272 | 0.00315 | 0.00317 | 0.00333 | 0.00343 | 0.00352 | 0.00373 | 18 |
WER | 0.00240 | 0.00224 | 0.00220 | 0.00252 | 0.00239 | 0.00260 | 0.00254 | 19 |
ngram | 0.00263 | 0.00239 | 0.00235 | 0.00227 | 0.00221 | 0.00202 | 0.00192 | 20 |
subset | 0.00197 | 0.00204 | 0.00201 | 0.00212 | 0.00208 | 0.00216 | 0.00218 | 21 |
recognizer | 0.00076 | 0.00047 | 0.00023 | 0.00015 | 0.00000 | 0.00000 | 0.00000 | 22 |
predicate | 0.00174 | 0.00178 | 0.00180 | 0.00185 | 0.00222 | 0.00192 | 0.00214 | 23 |
MFCC | 0.00172 | 0.00181 | 0.00141 | 0.00165 | 0.00105 | 0.00122 | 0.00066 | 24 |
formant | 0.00092 | 0.00069 | 0.00058 | 0.00054 | 0.00032 | 0.00031 | 0.00000 | 25 |
normalization | 0.00185 | 0.00176 | 0.00181 | 0.00191 | 0.00174 | 0.00172 | 0.00163 | 26 |
clustering | 0.00164 | 0.00168 | 0.00157 | 0.00149 | 0.00125 | 0.00113 | 0.00090 | 27 |
kernel | 0.00174 | 0.00178 | 0.00156 | 0.00172 | 0.00152 | 0.00151 | 0.00102 | 28 |
covariance | 0.00104 | 0.00130 | 0.00108 | 0.00124 | 0.00096 | 0.00117 | 0.00097 | 29 |
bigram | 0.00129 | 0.00137 | 0.00130 | 0.00130 | 0.00119 | 0.00114 | 0.00109 | 30 |
annotator | 0.00296 | 0.00200 | 0.00248 | 0.00189 | 0.00228 | 0.00129 | 0.00164 | 31 |
optimization | 0.00167 | 0.00196 | 0.00192 | 0.00210 | 0.00195 | 0.00216 | 0.00211 | 32 |
dialog | 0.00079 | 0.00125 | 0.00101 | 0.00135 | 0.00147 | 0.00162 | 0.00159 | 33 |
entropy | 0.00114 | 0.00142 | 0.00135 | 0.00146 | 0.00143 | 0.00147 | 0.00148 | 34 |
semantic | 0.00145 | 0.00146 | 0.00159 | 0.00166 | 0.00199 | 0.00189 | 0.00211 | 35 |
gaussian | 0.00078 | 0.00097 | 0.00072 | 0.00083 | 0.00050 | 0.00064 | 0.00051 | 36 |
WordNet | 0.00152 | 0.00124 | 0.00146 | 0.00134 | 0.00160 | 0.00121 | 0.00141 | 37 |
derivation | 0.00085 | 0.00081 | 0.00065 | 0.00054 | 0.00042 | 0.00032 | 0.00003 | 38 |
filtering | 0.00106 | 0.00090 | 0.00087 | 0.00077 | 0.00060 | 0.00044 | 0.00030 | 39 |
codebook | 0.00021 | 0.00035 | 0.00029 | 0.00041 | 0.00027 | 0.00031 | 0.00036 | 40 |
NLP | 0.00172 | 0.00139 | 0.00163 | 0.00152 | 0.00178 | 0.00151 | 0.00172 | 41 |
TREC | 0.00035 | 0.00046 | 0.00032 | 0.00022 | 0.00004 | 0.00000 | 0.00000 | 42 |
MAP | 0.00076 | 0.00075 | 0.00073 | 0.00072 | 0.00042 | 0.00040 | 0.00027 | 43 |
estimator | 0.00078 | 0.00128 | 0.00120 | 0.00152 | 0.00151 | 0.00192 | 0.00205 | 44 |
decoder | 0.00082 | 0.00084 | 0.00072 | 0.00074 | 0.00059 | 0.00060 | 0.00043 | 45 |
tagger | 0.00113 | 0.00063 | 0.00070 | 0.00047 | 0.00038 | 0.00000 | 0.00000 | 46 |
EM | 0.00084 | 0.00085 | 0.00065 | 0.00056 | 0.00039 | 0.00031 | 0.00003 | 47 |
disambiguation | 0.00091 | 0.00069 | 0.00073 | 0.00056 | 0.00054 | 0.00020 | 0.00021 | 48 |
syntactic | 0.00087 | 0.00072 | 0.00073 | 0.00066 | 0.00077 | 0.00058 | 0.00057 | 49 |
spectral | 0.00075 | 0.00081 | 0.00073 | 0.00082 | 0.00067 | 0.00078 | 0.00069 | 50 |
trigram | 0.00072 | 0.00056 | 0.00050 | 0.00050 | 0.00037 | 0.00033 | 0.00025 | 51 |
CRF | 0.00150 | 0.00160 | 0.00164 | 0.00171 | 0.00184 | 0.00173 | 0.00171 | 52 |
SMT | 0.00137 | 0.00135 | 0.00131 | 0.00137 | 0.00116 | 0.00108 | 0.00065 | 53 |
waveform | 0.00052 | 0.00051 | 0.00043 | 0.00045 | 0.00042 | 0.00047 | 0.00050 | 54 |
interpolation | 0.00055 | 0.00081 | 0.00074 | 0.00089 | 0.00078 | 0.00094 | 0.00095 | 55 |
quantization | 0.00023 | 0.00037 | 0.00029 | 0.00043 | 0.00032 | 0.00050 | 0.00044 | 56 |
VP | 0.00043 | 0.00035 | 0.00029 | 0.00015 | 0.00005 | 0.00000 | 0.00000 | 57 |
coder | 0.00034 | 0.00023 | 0.00024 | 0.00033 | 0.00019 | 0.00020 | 0.00025 | 58 |
Wikipedia | 0.00169 | 0.00169 | 0.00166 | 0.00166 | 0.00182 | 0.00178 | 0.00177 | 59 |
DNN | 0.00396 | 0.00668 | 0.00784 | 0.01044 | 0.01286 | 0.01609 | 0.01909 | 60 |
excitation | 0.00061 | 0.00056 | 0.00051 | 0.00058 | 0.00043 | 0.00048 | 0.00040 | 61 |
LDA | 0.00158 | 0.00175 | 0.00175 | 0.00197 | 0.00191 | 0.00219 | 0.00233 | 62 |
tweet | 0.00309 | 0.00273 | 0.00301 | 0.00309 | 0.00301 | 0.00309 | 0.00333 | 63 |
PP | 0.00042 | 0.00046 | 0.00039 | 0.00030 | 0.00032 | 0.00020 | 0.00019 | 64 |
summarization | 0.00097 | 0.00140 | 0.00136 | 0.00152 | 0.00177 | 0.00196 | 0.00213 | 65 |
BLEU | 0.00108 | 0.00139 | 0.00130 | 0.00147 | 0.00129 | 0.00138 | 0.00118 | 66 |
subband | 0.00057 | 0.00059 | 0.00047 | 0.00057 | 0.00041 | 0.00054 | 0.00055 | 67 |
ontology | 0.00099 | 0.00053 | 0.00081 | 0.00030 | 0.00071 | 0.00000 | 0.00049 | 68 |
error rate | 0.00046 | 0.00043 | 0.00033 | 0.00035 | 0.00022 | 0.00021 | 0.00014 | 69 |
intelligibility | 0.00137 | 0.00125 | 0.00137 | 0.00145 | 0.00157 | 0.00167 | 0.00182 | 70 |
prosody | 0.00059 | 0.00043 | 0.00041 | 0.00031 | 0.00022 | 0.00018 | 0.00006 | 71 |
treebank | 0.00131 | 0.00080 | 0.00103 | 0.00076 | 0.00087 | 0.00044 | 0.00043 | 72 |
preposition | 0.00101 | 0.00044 | 0.00035 | 0.00011 | 0.00000 | 0.00000 | 0.00000 | 73 |
MLP | 0.00080 | 0.00038 | 0.00005 | 0.00000 | 0.00000 | 0.00000 | 0.00000 | 74 |
perplexity | 0.00063 | 0.00076 | 0.00069 | 0.00087 | 0.00085 | 0.00099 | 0.00107 | 75 |
suffix | 0.00067 | 0.00052 | 0.00053 | 0.00048 | 0.00035 | 0.00016 | 0.00007 | 76 |
Viterbi | 0.00045 | 0.00036 | 0.00028 | 0.00021 | 0.00007 | 0.00000 | 0.00000 | 77 |
LPC | 0.00020 | 0.00026 | 0.00017 | 0.00029 | 0.00018 | 0.00031 | 0.00032 | 78 |
TTS | 0.00045 | 0.00058 | 0.00044 | 0.00053 | 0.00044 | 0.00053 | 0.00044 | 79 |
decomposition | 0.00073 | 0.00085 | 0.00085 | 0.00088 | 0.00089 | 0.00095 | 0.00103 | 80 |
polarity | 0.00156 | 0.00125 | 0.00129 | 0.00123 | 0.00131 | 0.00108 | 0.00092 | 81 |
acoustic | 0.00093 | 0.00071 | 0.00068 | 0.00069 | 0.00061 | 0.00060 | 0.00047 | 82 |
bandwidth | 0.00049 | 0.00050 | 0.00046 | 0.00053 | 0.00045 | 0.00056 | 0.00049 | 83 |
unigram | 0.00112 | 0.00093 | 0.00094 | 0.00090 | 0.00083 | 0.00068 | 0.00060 | 84 |
morpheme | 0.00054 | 0.00042 | 0.00037 | 0.00024 | 0.00022 | 0.00013 | 0.00001 | 85 |
synset | 0.00115 | 0.00083 | 0.00106 | 0.00087 | 0.00101 | 0.00059 | 0.00085 | 86 |
trajectory | 0.00054 | 0.00052 | 0.00035 | 0.00025 | 0.00000 | 0.00000 | 0.00000 | 87 |
robustness | 0.00066 | 0.00079 | 0.00074 | 0.00085 | 0.00078 | 0.00089 | 0.00089 | 88 |
Mel | 0.00097 | 0.00100 | 0.00102 | 0.00115 | 0.00116 | 0.00134 | 0.00146 | 89 |
coreference | 0.00115 | 0.00096 | 0.00101 | 0.00088 | 0.00090 | 0.00067 | 0.00073 | 90 |
heuristic | 0.00055 | 0.00053 | 0.00053 | 0.00048 | 0.00049 | 0.00032 | 0.00029 | 91 |
NE | 0.00066 | 0.00027 | 0.00021 | 0.00000 | 0.00000 | 0.00000 | 0.00000 | 92 |
modifier | 0.00068 | 0.00053 | 0.00058 | 0.00041 | 0.00042 | 0.00021 | 0.00017 | 93 |
decoding | 0.00065 | 0.00078 | 0.00063 | 0.00074 | 0.00064 | 0.00074 | 0.00053 | 94 |
triphone | 0.00045 | 0.00042 | 0.00029 | 0.00038 | 0.00016 | 0.00023 | 0.00010 | 95 |
NIST | 0.00067 | 0.00052 | 0.00045 | 0.00035 | 0.00010 | 0.00000 | 0.00000 | 96 |
paraphrase | 0.00079 | 0.00111 | 0.00114 | 0.00105 | 0.00126 | 0.00121 | 0.00148 | 97 |
cosine | 0.00106 | 0.00110 | 0.00117 | 0.00124 | 0.00128 | 0.00135 | 0.00148 | 98 |
predictor | 0.00043 | 0.00036 | 0.00035 | 0.00028 | 0.00017 | 0.00007 | 0.00006 | 99 |
mandarin | 0.00077 | 0.00057 | 0.00060 | 0.00056 | 0.00050 | 0.00046 | 0.00035 | 100 |
punctuation | 0.00076 | 0.00069 | 0.00078 | 0.00070 | 0.00068 | 0.00052 | 0.00063 | 101 |
spectrogram | 0.00092 | 0.00131 | 0.00140 | 0.00166 | 0.00177 | 0.00209 | 0.00237 | 102 |
mismatch | 0.00058 | 0.00059 | 0.00054 | 0.00061 | 0.00047 | 0.00051 | 0.00043 | 103 |
antecedent | 0.00039 | 0.00036 | 0.00035 | 0.00031 | 0.00028 | 0.00009 | 0.00009 | 104 |
co-occurrence | 0.00077 | 0.00059 | 0.00062 | 0.00046 | 0.00045 | 0.00024 | 0.00020 | 105 |
Fourier | 0.00035 | 0.00049 | 0.00044 | 0.00053 | 0.00051 | 0.00066 | 0.00069 | 106 |
IR | 0.00032 | 0.00051 | 0.00047 | 0.00054 | 0.00050 | 0.00057 | 0.00060 | 107 |
subspace | 0.00057 | 0.00069 | 0.00067 | 0.00084 | 0.00078 | 0.00091 | 0.00098 | 108 |
lexical | 0.00058 | 0.00049 | 0.00051 | 0.00047 | 0.00048 | 0.00034 | 0.00033 | 109 |
labeling | 0.00062 | 0.00071 | 0.00068 | 0.00074 | 0.00079 | 0.00076 | 0.00078 | 110 |
LR | 0.00080 | 0.00057 | 0.00071 | 0.00062 | 0.00075 | 0.00054 | 0.00070 | 111 |
reverberation | 0.00089 | 0.00096 | 0.00095 | 0.00101 | 0.00099 | 0.00115 | 0.00114 | 112 |
optimal | 0.00046 | 0.00056 | 0.00052 | 0.00060 | 0.00053 | 0.00062 | 0.00059 | 113 |
posterior | 0.00073 | 0.00083 | 0.00079 | 0.00083 | 0.00074 | 0.00081 | 0.00075 | 114 |
DT | 0.00065 | 0.00050 | 0.00053 | 0.00044 | 0.00040 | 0.00028 | 0.00028 | 115 |
collocation | 0.00045 | 0.00019 | 0.00023 | 0.00000 | 0.00003 | 0.00000 | 0.00000 | 116 |
SD | 0.00072 | 0.00078 | 0.00081 | 0.00093 | 0.00102 | 0.00116 | 0.00122 | 117 |
VQ | 0.00020 | 0.00008 | 0.00000 | 0.00000 | 0.00000 | 0.00000 | 0.00000 | 118 |
prefix | 0.00054 | 0.00055 | 0.00061 | 0.00058 | 0.00062 | 0.00052 | 0.00062 | 119 |
MLLR | 0.00030 | 0.00014 | 0.00005 | 0.00012 | 0.00000 | 0.00000 | 0.00000 | 120 |
Thus | 0.00035 | 0.00036 | 0.00033 | 0.00033 | 0.00029 | 0.00029 | 0.00026 | 121 |
encoding | 0.00040 | 0.00051 | 0.00056 | 0.00056 | 0.00065 | 0.00066 | 0.00081 | 122 |
DFT | 0.00036 | 0.00036 | 0.00036 | 0.00035 | 0.00032 | 0.00034 | 0.00032 | 123 |
acoustics | 0.00021 | 0.00025 | 0.00024 | 0.00025 | 0.00024 | 0.00030 | 0.00030 | 124 |
pruning | 0.00055 | 0.00032 | 0.00031 | 0.00018 | 0.00009 | 0.00000 | 0.00000 | 125 |
audio | 0.00068 | 0.00075 | 0.00073 | 0.00078 | 0.00077 | 0.00080 | 0.00083 | 126 |
histogram | 0.00046 | 0.00047 | 0.00040 | 0.00037 | 0.00027 | 0.00022 | 0.00016 | 127 |
transducer | 0.00046 | 0.00029 | 0.00032 | 0.00018 | 0.00018 | 0.00001 | 0.00002 | 128 |
talker | 0.00040 | 0.00029 | 0.00026 | 0.00019 | 0.00012 | 0.00007 | 0.00000 | 129 |
formalism | 0.00023 | 0.00019 | 0.00017 | 0.00013 | 0.00014 | 0.00007 | 0.00004 | 130 |
modality | 0.00051 | 0.00040 | 0.00043 | 0.00032 | 0.00038 | 0.00017 | 0.00021 | 131 |
propagation | 0.00077 | 0.00089 | 0.00093 | 0.00104 | 0.00106 | 0.00122 | 0.00127 | 132 |
FFT | 0.00022 | 0.00027 | 0.00022 | 0.00026 | 0.00020 | 0.00027 | 0.00029 | 133 |
phonetic | 0.00034 | 0.00030 | 0.00029 | 0.00027 | 0.00023 | 0.00021 | 0.00016 | 134 |
harmonic | 0.00048 | 0.00051 | 0.00048 | 0.00057 | 0.00046 | 0.00055 | 0.00055 | 135 |
autocorrelation | 0.00019 | 0.00011 | 0.00006 | 0.00001 | 0.00000 | 0.00000 | 0.00000 | 136 |
XML | 0.00052 | 0.00013 | 0.00031 | 0.00000 | 0.00015 | 0.00000 | 0.00000 | 137 |
Timit | 0.00040 | 0.00052 | 0.00043 | 0.00047 | 0.00035 | 0.00042 | 0.00036 | 138 |
articulation | 0.00040 | 0.00034 | 0.00033 | 0.00037 | 0.00033 | 0.00029 | 0.00028 | 139 |
WSD | 0.00044 | 0.00036 | 0.00042 | 0.00032 | 0.00026 | 0.00005 | 0.00005 | 140 |
cepstrum | 0.00030 | 0.00015 | 0.00012 | 0.00019 | 0.00013 | 0.00013 | 0.00008 | 141 |
UBM | 0.00069 | 0.00078 | 0.00057 | 0.00059 | 0.00032 | 0.00046 | 0.00014 | 142 |
morphology | 0.00046 | 0.00034 | 0.00036 | 0.00031 | 0.00028 | 0.00012 | 0.00004 | 143 |
linear | 0.00048 | 0.00054 | 0.00054 | 0.00062 | 0.00064 | 0.00073 | 0.00076 | 144 |
temporal | 0.00052 | 0.00045 | 0.00047 | 0.00046 | 0.00043 | 0.00033 | 0.00029 | 145 |
subtree | 0.00046 | 0.00040 | 0.00042 | 0.00040 | 0.00039 | 0.00033 | 0.00030 | 146 |
analyzer | 0.00033 | 0.00018 | 0.00019 | 0.00006 | 0.00002 | 0.00000 | 0.00000 | 147 |
Bayes | 0.00043 | 0.00043 | 0.00036 | 0.00034 | 0.00024 | 0.00019 | 0.00005 | 148 |
EER | 0.00054 | 0.00058 | 0.00046 | 0.00048 | 0.00029 | 0.00040 | 0.00023 | 149 |
residual | 0.00029 | 0.00028 | 0.00019 | 0.00019 | 0.00004 | 0.00005 | 0.00000 | 150 |
VAD | 0.00065 | 0.00051 | 0.00050 | 0.00046 | 0.00037 | 0.00035 | 0.00026 | 151 |
polynomial | 0.00015 | 0.00023 | 0.00020 | 0.00021 | 0.00020 | 0.00022 | 0.00023 | 152 |
eigenvalue | 0.00026 | 0.00029 | 0.00030 | 0.00033 | 0.00033 | 0.00039 | 0.00042 | 153 |
tuple | 0.00056 | 0.00045 | 0.00047 | 0.00040 | 0.00031 | 0.00020 | 0.00002 | 154 |
concatenation | 0.00037 | 0.00041 | 0.00037 | 0.00045 | 0.00044 | 0.00054 | 0.00056 | 155 |
www | 0.00067 | 0.00053 | 0.00055 | 0.00049 | 0.00051 | 0.00029 | 0.00047 | 156 |
transliteration | 0.00033 | 0.00028 | 0.00025 | 0.00011 | 0.00000 | 0.00000 | 0.00000 | 157 |
toolkit | 0.00067 | 0.00068 | 0.00068 | 0.00071 | 0.00071 | 0.00072 | 0.00070 | 158 |
tuning | 0.00067 | 0.00090 | 0.00093 | 0.00110 | 0.00114 | 0.00130 | 0.00138 | 159 |
negation | 0.00066 | 0.00061 | 0.00069 | 0.00056 | 0.00060 | 0.00039 | 0.00054 | 160 |
referent | 0.00027 | 0.00026 | 0.00029 | 0.00025 | 0.00029 | 0.00022 | 0.00031 | 161 |
CL | 0.00026 | 0.00027 | 0.00024 | 0.00024 | 0.00019 | 0.00018 | 0.00017 | 162 |
multiplication | 0.00027 | 0.00030 | 0.00033 | 0.00036 | 0.00038 | 0.00043 | 0.00048 | 163 |
initialization | 0.00049 | 0.00060 | 0.00060 | 0.00060 | 0.00065 | 0.00072 | 0.00078 | 164 |
thesaurus | 0.00035 | 0.00020 | 0.00029 | 0.00018 | 0.00026 | 0.00004 | 0.00009 | 165 |
DP | 0.00027 | 0.00030 | 0.00027 | 0.00029 | 0.00021 | 0.00018 | 0.00008 | 166 |
QA | 0.00021 | 0.00043 | 0.00042 | 0.00047 | 0.00047 | 0.00054 | 0.00053 | 167 |
schema | 0.00038 | 0.00035 | 0.00033 | 0.00029 | 0.00032 | 0.00024 | 0.00019 | 168 |
inverse | 0.00032 | 0.00031 | 0.00033 | 0.00032 | 0.00030 | 0.00030 | 0.00031 | 169 |
RNN | 0.00102 | 0.00275 | 0.00301 | 0.00417 | 0.00505 | 0.00656 | 0.00785 | 170 |
binary | 0.00045 | 0.00051 | 0.00052 | 0.00054 | 0.00051 | 0.00052 | 0.00052 | 171 |
subtraction | 0.00021 | 0.00019 | 0.00007 | 0.00003 | 0.00000 | 0.00000 | 0.00000 | 172 |
grapheme | 0.00040 | 0.00047 | 0.00048 | 0.00058 | 0.00062 | 0.00067 | 0.00070 | 173 |
indexing | 0.00023 | 0.00018 | 0.00014 | 0.00009 | 0.00005 | 0.00000 | 0.00000 | 174 |
argmax | 0.00034 | 0.00054 | 0.00048 | 0.00058 | 0.00055 | 0.00063 | 0.00064 | 175 |
abbreviation | 0.00055 | 0.00020 | 0.00024 | 0.00014 | 0.00022 | 0.00000 | 0.00000 | 176 |
regularization | 0.00073 | 0.00116 | 0.00116 | 0.00144 | 0.00153 | 0.00184 | 0.00199 | 177 |
dimensionality | 0.00054 | 0.00073 | 0.00076 | 0.00088 | 0.00092 | 0.00105 | 0.00117 | 178 |
convolution | 0.00035 | 0.00082 | 0.00089 | 0.00118 | 0.00140 | 0.00179 | 0.00214 | 179 |
MUC | 0.00012 | 0.00008 | 0.00004 | 0.00001 | 0.00000 | 0.00000 | 0.00000 | 180 |
vertex | 0.00055 | 0.00051 | 0.00046 | 0.00045 | 0.00040 | 0.00041 | 0.00033 | 181 |
quantizer | 0.00005 | 0.00006 | 0.00006 | 0.00008 | 0.00000 | 0.00006 | 0.00002 | 182 |
test set | 0.00051 | 0.00054 | 0.00054 | 0.00060 | 0.00060 | 0.00064 | 0.00064 | 183 |
fricative | 0.00017 | 0.00022 | 0.00017 | 0.00023 | 0.00018 | 0.00022 | 0.00014 | 184 |
RST | 0.00022 | 0.00021 | 0.00014 | 0.00026 | 0.00023 | 0.00033 | 0.00035 | 185 |
scaling | 0.00026 | 0.00032 | 0.00030 | 0.00033 | 0.00031 | 0.00034 | 0.00032 | 186 |
synthesizer | 0.00015 | 0.00013 | 0.00010 | 0.00012 | 0.00006 | 0.00007 | 0.00003 | 187 |
entailment | 0.00050 | 0.00032 | 0.00035 | 0.00015 | 0.00015 | 0.00000 | 0.00000 | 188 |
DCT | 0.00034 | 0.00027 | 0.00026 | 0.00023 | 0.00016 | 0.00010 | 0.00011 | 189 |
codec | 0.00014 | 0.00050 | 0.00044 | 0.00062 | 0.00074 | 0.00092 | 0.00112 | 190 |
MMSE | 0.00036 | 0.00042 | 0.00038 | 0.00041 | 0.00034 | 0.00032 | 0.00027 | 191 |
SN | 0.00041 | 0.00040 | 0.00039 | 0.00039 | 0.00040 | 0.00044 | 0.00042 | 192 |
PCA | 0.00051 | 0.00044 | 0.00048 | 0.00048 | 0.00046 | 0.00047 | 0.00052 | 193 |
beamformer | 0.00044 | 0.00058 | 0.00058 | 0.00073 | 0.00066 | 0.00082 | 0.00087 | 194 |
FIR | 0.00011 | 0.00010 | 0.00010 | 0.00009 | 0.00006 | 0.00004 | 0.00006 | 195 |
centroid | 0.00027 | 0.00032 | 0.00028 | 0.00028 | 0.00027 | 0.00027 | 0.00027 | 196 |
metadata | 0.00068 | 0.00023 | 0.00042 | 0.00014 | 0.00027 | 0.00000 | 0.00003 | 197 |
PLP | 0.00042 | 0.00030 | 0.00016 | 0.00015 | 0.00000 | 0.00000 | 0.00000 | 198 |
automaton | 0.00018 | 0.00020 | 0.00021 | 0.00020 | 0.00020 | 0.00019 | 0.00025 | 199 |
OOV | 0.00049 | 0.00065 | 0.00065 | 0.00075 | 0.00085 | 0.00100 | 0.00113 | 200 |
Top terms for last year / current year / next 5 years |
2014 | 2015 | prediction N+1 | prediction N+2 | prediction N+3 | prediction N+4 | prediction N+5 | rank |
annotation | dataset | DNN | DNN | DNN | DNN | DNN | 1 |
POS | DNN | dataset | dataset | dataset | dataset | dataset | 2 |
dataset | LM | annotation | neural network | neural network | neural network | neural network | 3 |
SR | SR | neural network | LM | RNN | RNN | RNN | 4 |
LM | classifier | POS | SR | POS | LM | SR | 5 |
classifier | neural network | SR | classifier | annotation | SR | POS | 6 |
DNN | HMM | LM | HMM | SR | HMM | LM | 7 |
HMM | POS | classifier | POS | LM | POS | metric | 8 |
GMM | annotation | HMM | RNN | classifier | classifier | HMM | 9 |
neural network | parser | parser | parser | metric | metric | parser | 10 |
parser | GMM | metric | metric | HMM | SNR | SNR | 11 |
tweet | metric | RNN | SNR | parser | parser | tweet | 12 |
annotator | SNR | tweet | GMM | tweet | tweet | classifier | 13 |
SNR | RNN | GMM | tweet | SNR | MT | parsing | 14 |
SVM | tweet | SNR | annotation | MT | WER | MT | 15 |
metric | MT | annotator | MT | parsing | parsing | WER | 16 |
ngram | SVM | ngram | WER | WER | GMM | spectrogram | 17 |
segmentation | ngram | MT | parsing | GMM | LDA | LDA | 18 |
WER | segmentation | parsing | ngram | annotator | optimization | annotation | 19 |
NP | parsing | SVM | subset | predicate | subset | subset | 20 |
MT | WER | segmentation | optimization | ngram | spectrogram | convolution | 21 |
parsing | iteration | WER | SVM | subset | ngram | predicate | 22 |
subset | NP | subset | iteration | semantic | summarization | summarization | 23 |
iteration | subset | optimization | LDA | optimization | predicate | semantic | 24 |
normalization | annotator | iteration | normalization | LDA | estimator | optimization | 25 |
kernel | optimization | normalization | annotator | CRF | semantic | estimator | 26 |
predicate | LSTM | predicate | segmentation | Wikipedia | regularization | regularization | 27 |
NLP | MFCC | LDA | predicate | NLP | iteration | ngram | 28 |
MFCC | predicate | NP | kernel | summarization | convolution | intelligibility | 29 |
Wikipedia | kernel | Wikipedia | CRF | spectrogram | Wikipedia | Wikipedia | 30 |
optimization | normalization | CRF | spectrogram | normalization | CRF | NLP | 31 |
clustering | LDA | NLP | semantic | iteration | normalization | CRF | 32 |
LDA | Wikipedia | semantic | Wikipedia | WordNet | intelligibility | annotator | 33 |
polarity | clustering | clustering | MFCC | SVM | dialog | normalization | 34 |
WordNet | CRF | kernel | estimator | segmentation | NLP | dialog | 35 |
CRF | semantic | WordNet | NLP | intelligibility | kernel | GMM | 36 |
semantic | entropy | MFCC | summarization | regularization | entropy | iteration | 37 |
intelligibility | summarization | spectrogram | clustering | kernel | BLEU | entropy | 38 |
SMT | BLEU | intelligibility | BLEU | estimator | cosine | cosine | 39 |
treebank | NLP | summarization | entropy | dialog | Mel | paraphrase | 40 |
bigram | bigram | entropy | intelligibility | entropy | tuning | Mel | 41 |
synset | SMT | SMT | regularization | convolution | annotator | WordNet | 42 |
coreference | spectrogram | BLEU | SMT | polarity | SVM | tuning | 43 |
entropy | covariance | bigram | dialog | BLEU | MFCC | propagation | 44 |
tagger | estimator | polarity | WordNet | cosine | propagation | SD | 45 |
unigram | polarity | estimator | bigram | paraphrase | paraphrase | BLEU | 46 |
BLEU | dialog | cosine | covariance | clustering | WordNet | dimensionality | 47 |
filtering | intelligibility | regularization | cosine | bigram | covariance | reverberation | 48 |
cosine | WordNet | paraphrase | polarity | Mel | SD | OOV | 49 |
covariance | regularization | covariance | convolution | SMT | reverberation | codec | 50 |
RNN | paraphrase | synset | Mel | tuning | bigram | bigram | 51 |
preposition | cosine | treebank | NP | propagation | clustering | perplexity | 52 |
ontology | sparsity | Mel | tuning | MFCC | polarity | decomposition | 53 |
summarization | Mel | dialog | paraphrase | SD | SMT | kernel | 54 |
NMF | gaussian | coreference | propagation | synset | segmentation | subspace | 55 |
Mel | coreference | reverberation | reverberation | NP | dimensionality | covariance | 56 |
acoustic | reverberation | unigram | SD | reverberation | OOV | interpolation | 57 |
spectrogram | unigram | propagation | unigram | covariance | perplexity | polarity | 58 |
formant | filtering | tuning | interpolation | dimensionality | decomposition | clustering | 59 |
disambiguation | tuning | convolution | dimensionality | coreference | interpolation | robustness | 60 |
reverberation | propagation | filtering | decomposition | decomposition | codec | segmentation | 61 |
syntactic | PLDA | decomposition | coreference | treebank | subspace | beamformer | 62 |
derivation | EM | ontology | perplexity | perplexity | robustness | synset | 63 |
EM | decomposition | SD | synset | OOV | beamformer | audio | 64 |
decoder | decoder | posterior | robustness | unigram | posterior | encoding | 65 |
LR | tensor | punctuation | subspace | labeling | audio | labeling | 66 |
MLP | synset | dimensionality | posterior | subspace | spectral | initialization | 67 |
dialog | posterior | robustness | gaussian | interpolation | labeling | linear | 68 |
paraphrase | convolution | interpolation | spectral | robustness | decoding | posterior | 69 |
gaussian | spectral | syntactic | audio | audio | linear | coreference | 70 |
estimator | derivation | audio | filtering | syntactic | initialization | LR | 71 |
mandarin | interpolation | disambiguation | treebank | LR | toolkit | toolkit | 72 |
propagation | treebank | MAP | OOV | posterior | annotation | grapheme | 73 |
co-occurrence | NMF | spectral | decoding | codec | unigram | spectral | 74 |
recognizer | robustness | gaussian | decoder | toolkit | coreference | Fourier | 75 |
punctuation | UBM | decoder | labeling | ontology | grapheme | MFCC | 76 |
MAP | decoding | LR | beamformer | punctuation | Fourier | SMT | 77 |
sparsity | SD | tagger | MAP | spectral | encoding | argmax | 78 |
spectral | RNNLM | negation | toolkit | beamformer | test set | test set | 79 |
regularization | perplexity | perplexity | punctuation | encoding | gaussian | punctuation | 80 |
posterior | MAP | toolkit | acoustic | initialization | argmax | prefix | 81 |
decomposition | audio | labeling | syntactic | decoding | optimal | unigram | 82 |
SD | dimensionality | acoustic | codec | linear | decoder | IR | 83 |
trigram | syntactic | subspace | LR | prefix | acoustic | optimal | 84 |
UBM | labeling | EM | linear | grapheme | synset | syntactic | 85 |
MWE | acoustic | OOV | mismatch | acoustic | syntactic | concatenation | 86 |
audio | subtask | derivation | test set | negation | IR | harmonic | 87 |
metadata | disambiguation | decoding | optimal | filtering | bandwidth | subband | 88 |
modifier | AMR | co-occurrence | initialization | test set | harmonic | negation | 89 |
suffix | subspace | prefix | UBM | decoder | QA | QA | 90 |
NIST | punctuation | mandarin | grapheme | argmax | LR | decoding | 91 |
www | formant | initialization | argmax | disambiguation | subband | PCA | 92 |
toolkit | softmax | beamformer | prefix | optimal | concatenation | binary | 93 |
tuning | epoch | formant | excitation | www | TTS | gaussian | 94 |
NE | toolkit | modifier | subband | binary | binary | SVM | 95 |
negation | sparse | UBM | harmonic | Fourier | prefix | waveform | 96 |
robustness | localization | encoding | EM | gaussian | punctuation | bandwidth | 97 |
VAD | OOV | www | encoding | mandarin | mismatch | ontology | 98 |
DT | connective | test set | mandarin | IR | quantization | multiplication | 99 |
decoding | tagger | mismatch | disambiguation | heuristic | excitation | acoustic | 100 |
perplexity | SemEval | linear | negation | lexical | PCA | www | 101 |
labeling | factorization | heuristic | IR | QA | waveform | quantization | 102 |
PLDA | negation | DT | formant | mismatch | mandarin | TTS | 103 |
excitation | DOA | suffix | binary | PCA | UBM | mismatch | 104 |
prosody | initialization | optimal | derivation | harmonic | SN | decoder | 105 |
mismatch | co-occurrence | binary | Fourier | co-occurrence | filtering | treebank | 106 |
lexical | mismatch | excitation | bandwidth | bandwidth | treebank | eigenvalue | 107 |
subband | subband | lexical | TTS | concatenation | multiplication | SN | 108 |
disfluency | EER | VAD | trigram | TTS | Timit | excitation | 109 |
subspace | TTS | trigram | www | excitation | vertex | codebook | 110 |
tuple | STFT | grapheme | PCA | temporal | EER | Timit | 111 |
heuristic | beamformer | argmax | heuristic | waveform | MAP | RST | 112 |
interpolation | mandarin | PCA | EER | modifier | negation | mandarin | 113 |
connective | LR | harmonic | suffix | derivation | eigenvalue | lexical | 114 |
abbreviation | bottleneck | temporal | tagger | MAP | VAD | vertex | 115 |
pruning | trigram | IR | Timit | subband | DFT | scaling | 116 |
vertex | excitation | tuple | QA | SN | lexical | LPC | 117 |
morpheme | optimal | subband | lexical | DT | scaling | DFT | 118 |
trajectory | ROUGE | bandwidth | co-occurrence | vertex | trigram | referent | 119 |
dimensionality | prefix | vertex | VAD | subtree | RST | inverse | 120 |
prefix | triple | EER | temporal | EM | temporal | filtering | 121 |
EER | AVG | NIST | waveform | multiplication | subtree | acoustics | 122 |
MSA | linear | codec | concatenation | modality | heuristic | subtree | 123 |
temporal | argmax | Fourier | vertex | tagger | derivation | FFT | 124 |
hypernym | test set | TTS | DT | VAD | MMSE | heuristic | 125 |
XML | modifier | modality | quantization | trigram | LPC | temporal | 126 |
subtask | ontology | Timit | codebook | suffix | codebook | NP | 127 |
waveform | www | waveform | MMSE | Timit | EM | DT | 128 |
modality | heuristic | QA | modifier | MMSE | formant | articulation | 129 |
RBM | PESQ | metadata | tuple | eigenvalue | inverse | MAP | 130 |
PCA | suffix | subtree | subtree | articulation | acoustics | centroid | 131 |
SemEval | Timit | WSD | SN | quantization | Thus | MMSE | 132 |
test set | trajectory | prosody | triphone | UBM | www | VAD | 133 |
hashtag | NIST | histogram | histogram | PP | articulation | Thus | 134 |
entailment | VAD | SN | articulation | DFT | DT | coder | 135 |
bandwidth | binary | PP | multiplication | formant | FFT | trigram | 136 |
initialization | IR | MMSE | NIST | schema | centroid | automaton | 137 |
OOV | encoding | morpheme | DFT | tuple | co-occurrence | EER | 138 |
harmonic | waveform | concatenation | error rate | scaling | NP | polynomial | 139 |
tensor | harmonic | morphology | Bayes | inverse | schema | disambiguation | 140 |
diarization | vertex | DFT | eigenvalue | EER | triphone | modality | 141 |
linear | codec | Bayes | scaling | referent | referent | co-occurrence | 142 |
subtree | DT | antecedent | Thus | Thus | fricative | schema | 143 |
TM | FN | preposition | coder | morphology | histogram | PP | 144 |
computer speech | bandwidth | entailment | inverse | antecedent | polynomial | modifier | 145 |
error rate | lexical | trajectory | WSD | codebook | error rate | CL | 146 |
morphology | Fourier | predictor | modality | metadata | phonetic | histogram | 147 |
transducer | recognizer | multiplication | prosody | centroid | modifier | phonetic | 148 |
histogram | encoder | error rate | antecedent | histogram | PP | UBM | 149 |
optimal | histogram | Thus | morphology | thesaurus | tuple | fricative | 150 |
Viterbi | Dirichlet | schema | ontology | WSD | disambiguation | error rate | 151 |
collocation | grapheme | articulation | PP | acoustics | coder | DCT | 152 |
TTS | hypernym | inverse | LPC | Bayes | automaton | triphone | 153 |
binary | bag of word | TREC | DP | phonetic | Bayes | antecedent | 154 |
triphone | TREC | transducer | schema | RST | DP | thesaurus | 155 |
WSD | PP | XML | centroid | prosody | CL | cepstrum | 156 |
beamformer | SVD | pruning | predictor | error rate | prosody | DP | 157 |
PESQ | loudspeaker | eigenvalue | phonetic | morpheme | modality | suffix | 158 |
Bayes | filterbank | scaling | RST | abbreviation | suffix | predictor | 159 |
predictor | sigmoid | referent | FFT | DP | morpheme | FIR | 160 |
LSA | tuple | triphone | referent | automaton | cepstrum | prosody | 161 |
VP | temporal | VP | trajectory | polynomial | morphology | WSD | 162 |
loudspeaker | pivot | thesaurus | acoustics | FFT | DCT | Bayes | 163 |
sparse | hyperparameter | codebook | morpheme | CL | antecedent | morphology | 164 |
readability | PSD | quantization | CL | coder | talker | formalism | 165 |
PLP | extractor | phonetic | fricative | transducer | synthesizer | derivation | 166 |
PP | PCA | Viterbi | DCT | LPC | formalism | synthesizer | 167 |
SN | preposition | centroid | TREC | fricative | predictor | EM | 168 |
epoch | prosody | DP | polynomial | predictor | quantizer | metadata | 169 |
talker | SLU | DCT | Viterbi | DCT | WSD | transducer | 170 |
articulation | QA | talker | automaton | triphone | residual | tuple | 171 |
grapheme | computer speech | transliteration | talker | entailment | thesaurus | quantizer | 172 |
encoding | error rate | CL | cepstrum | XML | FIR | morpheme | 173 |
triple | Bayes | abbreviation | residual | formalism | transducer | MLLR | 174 |
API | unsupervised | coder | thesaurus | cepstrum | MLLR | MLP | 175 |
Dirichlet | MMSE | acoustics | transducer | talker | MLP | MUC | 176 |
Timit | morpheme | recognizer | pruning | NIST | MUC | NE | 177 |
antecedent | RMSE | collocation | PLP | pruning | NE | NIST | 178 |
latent | triphone | FFT | VP | Viterbi | NIST | PLP | 179 |
STD | PMI | NE | recognizer | FIR | PLP | TREC | 180 |
STFT | perceptron | automaton | entailment | synthesizer | TREC | VP | 181 |
TF | RBM | polynomial | metadata | indexing | VP | VQ | 182 |
schema | DA | analyzer | abbreviation | VP | VQ | Viterbi | 183 |
extractor | concatenation | residual | formalism | residual | Viterbi | XML | 184 |
supervector | disfluency | formalism | synthesizer | TREC | XML | abbreviation | 185 |
concatenation | modality | fricative | MLLR | collocation | abbreviation | analyzer | 186 |
AVG | subtree | LPC | preposition | analyzer | analyzer | autocorrelation | 187 |
RMSE | minimization | PLP | transliteration | MLLR | autocorrelation | collocation | 188 |
bottleneck | MSE | RST | indexing | MLP | collocation | entailment | 189 |
SGMM | MR | indexing | FIR | MUC | entailment | formant | 190 |
MMSE | LS | cepstrum | quantizer | NE | indexing | indexing | 191 |
PMI | SN | FIR | analyzer | PLP | metadata | preposition | 192 |
localization | latent | synthesizer | subtraction | VQ | ontology | pruning | 193 |
IEEE International Conference | Tf Idf | subtraction | MUC | autocorrelation | preposition | recognizer | 194 |
DFT | PD | quantizer | autocorrelation | preposition | pruning | residual | 195 |
unsupervised | BLEU score | autocorrelation | MLP | quantizer | recognizer | subtraction | 196 |
perceptron | hashtag | MLP | NE | recognizer | subtraction | tagger | 197 |
speech communication | speech communication | MLLR | VQ | subtraction | tagger | talker | 198 |
HTML | MLP | MUC | XML | trajectory | trajectory | trajectory | 199 |
thesaurus | Dropout | VQ | collocation | transliteration | transliteration | transliteration | 200 |
Frequencies of the 15 top terms by year |
HMM | SR | LM | annotation | classifier | POS | NP | parser | segmentation | SNR | dataset | GMM | MT | neural network | iteration | |
2014 | 0.06389 | 0.08675 | 0.08323 | 0.13818 | 0.08029 | 0.09369 | 0.03628 | 0.05531 | 0.04216 | 0.04860 | 0.08763 | 0.05909 | 0.03621 | 0.05571 | 0.03300 |
2015 | 0.07693 | 0.08556 | 0.08557 | 0.07069 | 0.08248 | 0.07447 | 0.03484 | 0.05723 | 0.03917 | 0.05349 | 0.12078 | 0.05544 | 0.04556 | 0.08035 | 0.03743 |
2016 | 0.00067 | 0.00080 | 0.00079 | 0.00099 | 0.00078 | 0.00082 | 0.00029 | 0.00058 | 0.00039 | 0.00051 | 0.00126 | 0.00052 | 0.00040 | 0.00087 | 0.00033 |
2017 | 0.00074 | 0.00085 | 0.00088 | 0.00050 | 0.00078 | 0.00072 | 0.00019 | 0.00059 | 0.00032 | 0.00055 | 0.00146 | 0.00053 | 0.00049 | 0.00107 | 0.00035 |
2018 | 0.00059 | 0.00077 | 0.00076 | 0.00079 | 0.00068 | 0.00083 | 0.00018 | 0.00059 | 0.00028 | 0.00051 | 0.00163 | 0.00041 | 0.00044 | 0.00123 | 0.00030 |
2019 | 0.00073 | 0.00082 | 0.00084 | 0.00013 | 0.00065 | 0.00067 | 0.00004 | 0.00058 | 0.00019 | 0.00059 | 0.00192 | 0.00043 | 0.00054 | 0.00155 | 0.00033 |
2020 | 0.00062 | 0.00073 | 0.00070 | 0.00040 | 0.00053 | 0.00073 | 0.00005 | 0.00060 | 0.00016 | 0.00060 | 0.00210 | 0.00028 | 0.00047 | 0.00176 | 0.00027 |
total elapsed time (read and display included)= 1.0457833333333333 minutes with 8 cores
computed on: Mon Nov 14 19:52:10 CET 2016