Browse > Article

Large Vocabulary Continuous Speech Recognition Based on Language Model Network  

안동훈 (서강대학교 컴퓨터학과 음성언어처리연구실)
정민화 (서강대학교 컴퓨터학과 음성언어처리연구실)
Publication Information
The Journal of the Acoustical Society of Korea / v.21, no.6, 2002 , pp. 543-551 More about this Journal
Abstract
In this paper, we present an efficient decoding method that performs in real time for 20k word continuous speech recognition task. Basic search method is a one-pass Viterbi decoder on the search space constructed from the novel language model network. With the consistent search space representation derived from various language models by the LM network, we incorporate basic pruning strategies, from which tokens alive constitute a dynamic search space. To facilitate post-processing, it produces a word graph and a N-best list subsequently. The decoder is tested on the database of 20k words and evaluated with respect to accuracy and RTF.
Keywords
Large vocabulary continuous speech recognition; Language model network; Back-off N-gram; Token passing algorithm;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Language modelling for efficient beam search /
[ M.Federico;M.Cettolo;F.Brugnara;G.Antoniol ] / Computer, Speech and Language   DOI   ScienceOn
2 A word graph based n-best search in continuous speech recognition /
[ B.H.Tran;F.Seide;V.Steinbiss ] / Proc. ICSLP-96
3 Improved backing-off for m-gram language modeling /
[ R.Kneser;H.Ney ] / Proc. ICASSP-95
4 On the estimation of small probabilities by leaving-one-out /
[ H.Ney;U.Essen;R.Kneser ] / IEEE Transactions on Pattern Analysis and Machine Intelligence   DOI   ScienceOn
5 /
[ V.Drobot ] / Formal Languages and Automata Theory
6 의사형태소 단위의 연속 음성 인식 /
[ 이경님;정민화 ] / 제 15회 음성통신 및 신호처리 워크샵
7 The CUHTK-Entropic 10xRT Broadcast News Transcription System /
[ J.J.Odell ] / Proc DARPA Broadcast News Workshop
8 Estimation of Probabilities from sparse data for the language model component of a speech recognizer /
[ S.M.Katz ] / IEEE Transactions on Acoustics, Speech and Signal Processing
9 Improvements in Beam Search for 10000-Word Continuous Speech Recognition /
[ H.Ney;R. Haeb-Umbach;B.H.Tran;M.Oerder ] / Proc. ICASSP-92
10 A word graph algorithm for large vocabulary continuous speech recognition /
[ S.Ortmanns;H.Ney ] / Computer, Speech and Language   DOI   ScienceOn
11 Language-model look-ahead for large vocabulary speech recognition /
[ S.Ortmanns;H.Ney;A.Eiden ] / Proc. ICSLP-96
12 Data driven search organization for continuous speech recognition /
[ H.Ney;D.Mergel;A.Noll;A.Paeseler ] / IEEE Transactions on Signal Processing   DOI   ScienceOn
13 /
[ S.J.Young;N.H.Russell;J.H.S.Thornton ] / Token Passing: A Simple Conceptual Model for Connected Speech Recognition Systems, CUED-TR-38