Recent advances in automatic speech recognition

Recent advances in automatic speech recognition

Source :

• Signal Processing [ 0165-1684 ] ; 1979.

English descriptors

• Teeft :
  • Academic press, Acceptability judgements, Acoustic, Acoustic data, Acoustic parameters, Acoustic processing, Acoustic tubes, Acoustics, Adjacent words, Algorithm, Amer, Analysis frame, Analytic rules, April, Artificial intelligence, Artificial intelligence center, August, Automatic detection, Automatic recognition, Automatic segmentation, Automatic speech recognition, Automatic speech understanding system, Automaticspeech recognition, Backtracking, Best path, Better performances, Closest constituent, Composition rules, Comput, Computation time, Computational linguistics, Conf, Conference record, Confidence level, Consonant, Context dependencies, Context sensitivities, Contextual effects, Continuous speech, Continuous speech input, Continuous speech recognition, Control strategies, Correct sentence, Data base, Dictionary expansion, Different speakers, Different types, Different words, Dragon system, Dynamic programming, Electrical engineering dept, Electrotechnical laboratory, Event processing, Event queue, Factor statements, Feature extraction, Focus model, Formant, Fortran programs, Fourier analysis, Fuzzy relations, Fuzzy sets, Grammar, Grammatical structure, Harpy, Harpy system, Hearsay, Hierarchical machine, Homomorphic prediction, Hwim, Hwim system, Hypothesis, Ieee, Ieee conf, Ieee internat, Ieee lnternat, Ieee trans, Information processing, Information theory, Input sentence, Input utterance, Interesting papers, Internal report institute, Internat, Japanese sentences, Jelinek, Joint conf, June, Knowledge representation, Knowledge source, Knowledge sources, Laface, Language definition, Language model, Lattice, Lexical, Lexical classification, Lexical retrieval component, Linear prediction, Linguistic decoder, Linguistic information, Makhonine, Markov, Markov process, Membership function, Menlo park, Mori, Musashino labs, Nakagawa, Natural language, Node, Nonterminal symbols, Other phrases, Parser, Partial path, Pattern recognition, Phoneme, Phonemic events, Phonemic features, Phonemic hypotheses, Phonemic interpretations, Phonemic units, Phonetic, Phonetic features, Phonetic transcriptions, Phonological, Phonological rules, Possible interpretations, Practical applications, Precategorical classification, Precedence graph, Precondition pattern, Prediction, Proc, Prosodic aids, Prosodic component, Rabiner, Rechevoe obshenie, Rechi, Recognition system, Reddy, Reference templates, Regular grammar, Retrieval, Sakai, Same word, Search strategies, Search tree, Segmentation, Sekiguchi, Semantic interpretation, Semantic support, Semantics, Shigenaga, Shortfall, Shortfall score, Signal processing, Single word, Soviet union, Speech, Speech analysis, Speech patterns, Speech recognition, Speech recognition system, Speech recognition tasks, Speech research, Speech segmentation, Speech signal, Speech understanding, Speech understanding research, Speech understanding system, Speech understanding systems, Speech waveform, Speech waveforms, Stanford, Stanford research institute, Such systems, Syllabic, Syllable, Syntactic, Syntactic analysis, Syntactic decoding, Syntactic rules, Syntax, Syntax component, System organization, System performances, Time evolutions, Time interval, Total hypothesis, Trans, Transition networks, Tulsa, Understanding speech, Unified approach, Univ, Univac park, Unrecognized portion, Utterance, Various knowledge sources, Various levels, Voice input, Waveform, Word hypotheses, Word hypothesis, Word prediction, Word recognition, Word recognition systems, Word sequence, Word sequences, Word strings, Word task, Word verification.

Abstract

• https://api.istex.fr/ark:/67375/6H6-V2PXDCZJ-R/fulltext.pdf

Links toward previous steps (curation, corpus...)

• to stream Istex, to step Corpus: 003992
• to stream Istex, to step Curation: 003948
• to stream Istex, to step Checkpoint: 003A11

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00F785 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00F785 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    Main
   |étape=   Merge
   |type=    RBID
   |clé=     ISTEX:F18F09F3764BE894F91D879FD37E66582E7A723C
   |texte=   Recent advances in automatic speech recognition
}}

This area was generated with Dilib version V0.6.33. Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022