Progress in dynamic programming search for LVCSR

Initially introduced in the late 1960s and early 1970s, dynamic programming algorithms have become increasingly popular in automatic speech recognition. There are two reasons why this has occurred. First, the dynamic programming strategy can be combined with a very efficient and practical pruning strategy so that very large search spaces can be handled. Second, the dynamic programming strategy has turned out to be extremely flexible in adapting to new requirements. Examples of such requirements are the lexical tree organization of the pronunciation lexicon and the generation of a word graph instead of the single best sentence. We attempt to review the use of dynamic programming search strategies for large-vocabulary continuous speech recognition (LVCSR). The following methods are described in detail: searching using a lexical tree, language-model look-ahead and word-graph generation.

[1]  Steve J. Young,et al.  Large vocabulary continuous speech recognition using HTK , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Renato De Mori,et al.  High performance connected digit recognition using codebook exponents , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  F. Itakura,et al.  Minimum prediction residual principle applied to speech recognition , 1975 .

[4]  L. Mondshein,et al.  The CASPERS linguistic analysis system , 1975 .

[5]  Hermann Ney,et al.  Data driven search organization for continuous speech recognition , 1992, IEEE Trans. Signal Process..

[6]  Douglas B. Paul,et al.  Algorithms for an Optimal A* Search and Linearizing the Search in the Stack Decoder* , 1991, HLT.

[7]  Mei-Yuh Hwang,et al.  Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Enrico Bocchieri,et al.  Vector quantization for the efficient computation of continuous density likelihoods , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Steve Austin,et al.  The forward-backward search algorithm , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[10]  Hermann Ney,et al.  The use of a one-stage dynamic programming algorithm for connected word recognition , 1984 .

[11]  Michael D. Brown,et al.  An algorithm for connected word recognition , 1982, ICASSP.

[12]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[13]  Stefan Ortmanns,et al.  Dynamic programming search techniques for across-word modelling in speech recognition , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[14]  Lalit R. Bahl,et al.  Decoding for channels with insertions, deletions, and substitutions with applications to speech recognition , 1975, IEEE Trans. Inf. Theory.

[15]  Renato De Mori,et al.  A Cache-Based Natural Language Model for Speech Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  S. J. Young,et al.  Tree-based state tying for high accuracy acoustic modelling , 1994 .

[17]  Douglas B. Paul,et al.  An Efficient A* Stack Decoder Algorithm for Continuous Speech Recognition with a Stochastic Language Model , 1992, HLT.

[18]  Dennis H. Klatt,et al.  Review of the ARPA speech understanding project , 1990 .

[19]  Yves Normandin,et al.  Efficient lexical access strategies , 1993, EUROSPEECH.

[20]  Derick Wood,et al.  Data structures, algorithms, and performance , 1992 .

[21]  Hermann Ney,et al.  A word graph algorithm for large vocabulary continuous speech recognition , 1994, Comput. Speech Lang..

[22]  Prof. Dr. Kurt Mehlhorn,et al.  Data Structures and Algorithms 1 , 1984, EATCS.

[23]  George Zavaliagkos,et al.  Comparative Experiments on Large Vocabulary Speech Recognition , 1993, HLT.

[24]  Steve Renals,et al.  Efficient search using posterior phone probability estimates , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[25]  Hermann Ney,et al.  Extensions to the word graph method for large vocabulary continuous speech recognition , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[26]  Hermann Ney,et al.  Improvements in beam search for 10000-word continuous-speech recognition , 1994, IEEE Trans. Speech Audio Process..

[27]  J. Wolf,et al.  The HWIM speech understanding system , 1977 .

[28]  John D. Lafferty,et al.  Inference and Estimation of a Long-Range Trigram Model , 1994, ICGI.

[29]  Hermann Ney,et al.  Large vocabulary continuous speech recognition using word graphs , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[30]  H. Sakoe,et al.  Two-level DP-matching--A dynamic programming-based pattern matching algorithm for connected word recognition , 1979 .

[31]  Hermann Ney,et al.  Search Strategies For Large-Vocabulary Continuous-Speech Recognition , 1995 .

[32]  Hermann Ney,et al.  Fast likelihood computation methods for continuous mixture densities in large vocabulary speech recognition , 1997, EUROSPEECH.

[33]  R. Schwartz,et al.  A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[34]  Hermann Ney,et al.  Dynamic programming parsing for context-free grammars in continuous speech recognition , 1991, IEEE Trans. Signal Process..

[35]  T. K. Vintsyuk.  Speech discrimination by dynamic programming , 1968 .

[36]  Mei-Yuh Hwang,et al.  An improved search algorithm using incremental knowledge for continuous speech recognition , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[37]  James K. Baker,et al.  Stochastic modeling for automatic speech understanding , 1990 .

[38]  Hermann Ney,et al.  Word Triggers and the EM Algorithm , 1997, CoNLL.

[39]  Vassilios Digalakis,et al.  Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[40]  Andreas Noll,et al.  A data-driven organization of the dynamic programming beam search for continuous speech recognition , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[41]  Steve Renals,et al.  Efficient evaluation of the LVCSR search space using the NOWAY decoder , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[42]  N. Deshmukh,et al.  Hierarchical search for large-vocabulary conversational speech recognition: working toward a solution to the decoding problem , 1999 .

[43]  F. Jelinek,et al.  Continuous speech recognition by statistical methods , 1976, Proceedings of the IEEE.

[44]  Hermann Ney,et al.  A comparison of time conditioned and word conditioned search techniques for large vocabulary speech recognition , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[45]  Hermann Ney,et al.  Language-model look-ahead for large vocabulary speech recognition , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[46]  Steve J. Young,et al.  A One Pass Decoder Design For Large Vocabulary Recognition , 1994, HLT.

[47]  Xavier L. Aubert,et al.  One pass cross word decoding for large vocabularies based on a lexical tree search organization , 1999, EUROSPEECH.

[48]  Mei-Yuh Hwang,et al.  Improvements on the pronunciation prefix tree search organization , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[49]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[50]  Hiroaki Sakoe,et al.  A Dynamic Programming Approach to Continuous Speech Recognition , 1971 .

[51]  Peter Beyerlein,et al.  Hamming distance approximation for a fast log-likelihood computation for mixture densities , 1995, EUROSPEECH.

[52]  Victor Lesser,et al.  IN THE HEARSAY-II SPEECH UNDERSTANDING SYSTEM , 1976 .

[53]  H. Ney,et al.  Improvements in beam search for 10000-word continuous speech recognition , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[54]  Giuliano Antoniol,et al.  Language model representations for beam-search decoding , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[55]  Hermann Ney,et al.  Improved lexical tree search for large vocabulary speech recognition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[56]  Frank K. Soong,et al.  A Tree.Trellis Based Fast Search for Finding the N Best Sentence Hypotheses in Continuous Speech Recognition , 1990, HLT.

[57]  N. G. Zagoruyko,et al.  Automatic recognition of 200 words , 1970 .

[58]  Kurt Mehlhorn,et al.  Data Structures and Algorithms 1: Sorting and Searching , 2011, EATCS Monographs on Theoretical Computer Science.

[59]  Hermann Ney,et al.  Large vocabulary continuous speech recognition of Wall Street Journal data , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[60]  Mitch Weintraub,et al.  Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[61]  Lawrence R. Rabiner,et al.  Connected digit recognition using a level-building DTW algorithm , 1981 .

[62]  Peter Regel-Brietzmann,et al.  DP-based wordgraph pruning , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[63]  Qiru Zhou,et al.  An approach to continuous speech recognition based on layered self-adjusting decoding graph , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[64]  R. Bellman.  Dynamic programming. , 1957, Science.

[65]  Hermann Ney,et al.  Look-ahead techniques for fast beam search , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[66]  Lalit R. Bahl,et al.  A Maximum Likelihood Approach to Continuous Speech Recognition , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[67]  L. R. Rabiner,et al.  An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition , 1983, The Bell System Technical Journal.

[68]  Pietro Laface,et al.  Using grammars in forward and backward search , 1993, EUROSPEECH.

[69]  Hermann Ney,et al.  Word graphs: an efficient interface between continuous-speech recognition and language understanding , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[70]  Richard M. Schwartz,et al.  Single-tree method for grammar-directed search , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[71]  Hermann Ney,et al.  The Philips research system for large-vocabulary continuous-speech recognition , 1993, EUROSPEECH.

[72]  Stefan Ortmanns,et al.  High quality word graphs using forward-backward pruning , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[73]  Chin-Hui Lee,et al.  A frame-synchronous network search algorithm for connected word recognition , 1989, IEEE Trans. Acoust. Speech Signal Process..

[74]  Bruce Lowerre,et al.  The Harpy speech understanding system , 1990 .

[75]  Hermann Ney,et al.  Experimental analysis of the search space for 20 000-word speech recognition , 1995, EUROSPEECH.

[76]  Lori Lamel,et al.  The LIMSI continuous speech dictation system: evaluation on the ARPA Wall Street Journal task , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[77]  Hermann Ney,et al.  Improvements in beam search , 1994, ICSLP.