LVCSR log-likelihood ratio scoring for keyword spotting
作者： M. Weintraub
DOI: 10.1109/ICASSP.1995.479532
关键词:
摘要: A new scoring algorithm has been developed for generating wordspotting hypotheses and their associated scores. This technique uses a large-vocabulary continuous speech recognition (LVCSR) system to generate the N-best answers along with Viterbi alignments. The score putative hit is computed by summing likelihoods all that contain keyword normalized dividing sum of hypothesis in list. Using test set conversational from Switchboard Credit Card conversations, we achieved an 81% figure merit (FOM). Our word error rate on this same 54.7%.
sci-hub.se 参考文章(12)
B. Landell, R. Wohlford, L. Bahler, Improved speech recognition in noise international conference on acoustics, speech, and signal processing. ,vol. 11, pp. 749- 752 ,(1986) , 10.1109/ICASSP.1986.1169211
Hy Murveit, John Butzberger, Mitch Weintraub, Reduced channel dependence for speech recognition Proceedings of the workshop on Speech and Natural Language - HLT '91. pp. 280- 284 ,(1992) , 10.3115/1075527.1075593
F.K. Soong, E.-F. Huang, A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition international conference on acoustics, speech, and signal processing. pp. 705- 708 ,(1991) , 10.1109/ICASSP.1991.150437
M. Weintraub, Keyword-spotting using SRI's DECIPHER large-vocabulary speech-recognition system IEEE International Conference on Acoustics Speech and Signal Processing. ,vol. 2, pp. 463- 466 ,(1993) , 10.1109/ICASSP.1993.319341
Hy Murveit, John Butzberger, Mitch Weintraub, Performance of SRI's DECIPHER#8482; speech recognition system on DARPA's CSR task Proceedings of the workshop on Speech and Natural Language - HLT '91. pp. 410- 414 ,(1992) , 10.3115/1075527.1075625
J.R. Rohlicek, W. Russell, S. Roukos, H. Gish, Continuous hidden Markov modeling for speaker-independent word spotting international conference on acoustics, speech, and signal processing. pp. 627- 630 ,(1989) , 10.1109/ICASSP.1989.266505
Hy Murveit, Peter Monaco, Vassilios Digalakis, John Butzberger, Techniques to achieve an accurate real-time large-vocabulary speech recognition system Proceedings of the workshop on Human Language Technology - HLT '94. pp. 393- 398 ,(1994) , 10.3115/1075812.1075903
Richard Schwartz, Steve Austin, Efficient, high-performance algorithms for N-Best search human language technology. pp. 6- 11 ,(1990) , 10.3115/116580.116581
R.C. Rose, D.B. Paul, A hidden Markov model based keyword recognition system international conference on acoustics, speech, and signal processing. pp. 129- 132 ,(1990) , 10.1109/ICASSP.1990.115555
V. Digalakis, H. Murveit, Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 537- 540 ,(1994) , 10.1109/ICASSP.1994.389212