Towards Superhuman Speech Recognition

Springer Handbooks

Volumn , Issue , 2008, Pages 597-616

  Picheny, Michael ^a   Nahamoo, David ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Defense Advance Research Project Agency; Language Model; Speech Recognition; Speech Recognition System; Word Error Rate

Indexed keywords

EID: 77949481364     PISSN: 25228692     EISSN: 25228706     Source Type: Book Series    
DOI: 10.1007/978-3-540-49127-9_30     Document Type: Chapter

References (59)

1. J.G. Fiscus, W.M. Fisher, A.F. Martin, M.A. Przybocki, D.S. Pallett: 2000 NIST evaluation of conversational speech recognition over the telephone, Proc. 2000 Speech Transcription Workshop (2000)
2. A. Janin, D. Baron, J. Edwards, D. Ellis, D. Gel-bart, N. Morgan, B. Peskin, T. Pfau, E. Shriberg, A. Stolcke, C. Wooters: The ICSI Meeting corpus, Proc. ICASSP, Vol. 1 (2003) pp. 364–367
3. M. Padmanabhan, G. Saon, J. Huang, B. Kingsbury, L. Mangu: Automatic speech recognition performance on a voicemail transcription task, IEEE Trans. Speech Audio Process. 10(7), 433– 442(2002)
4. R.P. Lippmann: Speech recognition by machines and humans, Speech Commun. 22(1), 1–15 (1997)
5. I. Pollack, J.M. Pickett: The intelligibility of excerpts from conversation, Lang. Speech 6, 165–171 (1963)
6. E. Chang, R. Lippmann: Improving wordspotting performance with artificially generated data, Proc. ICASSP, Vol. 1 (1996) pp. 526–529
7. J.B. Allen: How do humans process and recognize speech?, IEEE Trans. Speech Audio Process. 2(4), 567–577 (1994)
8. C.E. Shannon: Prediction and entropy of printed English, Bell Syst. Tech. J. 30, 50–64 (1950)
9. NIST Speech Group: The Rich Transcription Spring 2003 (RT-03S) Evaluation Plan, Version 4 (2003) http://www.nist.gov/speech/tests/rt/rt2003/spring/docs/rt03-spring-eval-plan-v4.pdf
10. W. Byrne, D. Doermann, M. Franz, S. Gustman, J. Hajič, D. Oard, M. Picheny, J. Psutka, B. Ramabhadran, D. Soergel, T. Ward, W.-J. Zhu: Automatic recognition of spontaneous speech for access to multilingual oral history archives, IEEE Trans. Speech Audio Process. 12(4), 420–435 (2004)
11. I. Nastajus: http://en.wikipedia.org/wiki/Naturally Speeking (2007)
12. P. Woodland, H.Y. Chan, G. Evermann, M.J.F. Gales, D.Y. Kim, X.A. Liu, D. Mrva, K.C. Sim, L. Wang, K. Yu, J. Makhoul, R. Schwartz, L. Nguyen, S. Matsoukas, B. Xiang, M. Afify, S. Abdou, J.-L. Gauvain, L. Lamel, H. Schwenk, G. Adda, F. Lefevre, D. Vergyri, W. Wang, J. Zheng, A. Venkataraman, R.R. Gadde, A. Stolcke: SuperEARS: Multi-Site Broadcast News System, DARPA EARS 2004 Workshop (2007), http://www.sainc.com/richtrans2004/uploads/monday/EARS BN Super team.pdf
13. A. Aaron, S. Chen, P. Cohen, S. Dharanipragada, E. Eide, M. Franz, J.-M. Leroux, X. Luo, B. Maison, L. Mangu, T. Mathes, M. Novak, P. Olsen, M. Picheny, H. Printz, B. Ramabhadran, A. Sakra-jda, G. Saon, B. Tydlitat, K. Visweswariah, D. Yuk: Speech recognition for DARPA Communicator, Proc. ICASSP, Vol. 1 (2001) pp. 489–492
14. H. Soltau, B. Kingsbury, L. Mangu, D. Povey, G. Saon, G. Zweig: The IBM 2004 conversational telephony system for rich transcription, Proc. ICASSP, Vol. 1 (2005) pp. 205–208
15. J. Fiscus: The Rich Transcription Spring 2006 (RT-06S) Evaluation Results (NIST Speech Group, 2007) http://www.nist.gov/speech/tests/rt/rt2006/spring/pdfs/rt06s-STT-results-v7.pdf
16. G. Saon, M. Padmanbhan, R. Gopinath, S. Chen: Maximum likelihood discriminant feature spaces, Proc. ICASSP, Vol. 2 (2000) pp. 1129–1132
17. R.A. Gopinath: Maximum likelihood modeling with Gaussian distributions for classification, Proc. ICASSP, Vol. 2 (1998) pp. 661–664
18. M.J.F. Gales: Semi-tied full-covariance matrices for hidden Markov models, Vol. CUED/F-INFENG/TR287 (Cambridge Univ. Engineering Department, Cambridge 1997)
19. J. Huang, B. Kingsbury, L. Mangu, G. Saon, R. Sarikaya, G. Zweig: Improvements to the IBM hub 5e system, Proc. NIST RT-02 Workshop (2002)
20. G. Saon, G. Zweig, B. Kingsbury, L. Mangu, U. Chaudhari: An architecture for rapid decoding of large vocabulary conversational speech, Proc. Eurospeech, Vol. 3 (2003) pp. 1977–1981
21. S. Axelrod, V. Goel, B. Kingsbury, K. Visweswariah, R. Gopinath: Large vocabulary conversational speech recognition with a subspace constraint on inverse covariance matrices, Proc. Eurospeech, Vol. 3 (2003) pp. 1613–1616
22. S. Axelrod, R.A. Gopinath, P. Olsen: Modeling with a subspace constraint on inverse covariance matrices, Proc. Int. Conf. Spoken Lang. Process., Vol. 2 (2002) pp. 2177–2180
23. S. Wegmann, D. MacAllaster, J. Orloff, B. Peskin: Speaker normalization on conversational telephone speech, Proc. ICASSP, Vol. 1 (1996) pp. 339–342
24. M.J.F. Gales: Maximum likelihood linear transformations for HMM-based speech recognition, Vol. CUED/F-INFENG/TR291 (Cambridge Univ. Engineering Department, Cambridge 1997)
25. C.J. Leggetter, P.C. Woodland: Speaker adaptation of continuous density HMMs using multivariate linear regression, Proc. Int. Conf. Spoken Lang. Process., Vol. I (1994) pp. 451–454
26. S.F. Chen, J. Goodman: An empirical study of smoothing techniques for language modeling, Computer, Speech Lang. 13(4), 359–393 (1999)
27. L.R. Bahl, P.V. deSouza, P.S. Gopalakrishnan, D. Nahamoo, M. Picheny: Robust methods for using context-dependent features and models in a continuous speech recognizer, Proc. ICASSP, Vol. 1 (1994) pp. 533–536
28. M. Padmanabhan, G. Ramaswamy, B. Ramabhadran, P.S. Gopalakrishnan, C. Dunn: Issues involved in voicemail data collection, Proc. DARPA Broadcast News Transcription and Understanding Workshop (1998)
29. L. Mangu, E. Brill, A. Stolcke: Finding consensus in speech recognition: Word error minimization and other applications of confusion networks, Computer, Speech Lang. 14(4), 373–400 (2000)
30. E. Shriberg, A. Stolcke, D. Baron: Observations on overlap: Findings and implications for automatic processing of multi-party conversation, Proc. Eurospeech, Vol. 2 (2001) pp. 1359–1362
31. D. Povey, P. Woodland: Minimum phone error and I-smoothing for improved discriminative training, Proc. ICASSP, Vol. 1 (2002) pp. 105–108
32. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, G. Zweig: FMPE: Discriminatively trained features for speech recognition, Proc. ICASSP, Vol. 1 (2005) pp. 961–964
33. M. Padmanabhan, M. Picheny: Large-vocabulary speech recognition algorithms, IEEE Comput. 35(4), 42–50 (2002)
34. Google Desktop Developer Group: http://www. google.com/apis/(2007)
35. B.E.D. Kingsbury, N. Morgan, S. Greenberg: Robust speech recognition using the modulation spectrogram, Speech Commun. 25(1-3), 117–132 (1998)
36. M. Ostendorf, V.V. Digilakis, O.A. Kimball: From HMMs to segment models: A unified view of stochastic modeling for speech recognition, Proc. IEEE Trans. Speech Audio Process. 4(5), 360–378 (1996)
37. J. Bridle, L. Deng, J. Picone, H. Richards, J. Ma, T. Kamm, M. Schuster, S. Pike, R. Regan: An investigation of segmental hidden dynamic models of speech coarticulation for automatic speech recognition, Final Workshop Report, Center for Language and Speech Processing (The Johns Hopkins University, Baltimore 1998)
38. G. Zweig, M. Padmanabhan: Dependency modeling with Bayesian networks in a voicemail transcription system, Proc. Eurospeech, Vol. 3 (1999) pp. 1335–1338
39. J. Bilmes: Buried Markov models, Proc. ICASSP, Vol. 2 (1999) pp. 713–716
40. M. Padmanabhan: Use of spectral peak information in speech recognition, Proc. NIST Speech Transcription Workshop (2000)
41. Ö. Çetin, M. Ostendorf: Multi-rate and variable-rate modeling of speech at phone and syllable time scales, Proc. Int. Conf. Acoust. Speech Signal Process., Vol. 1 (2005) pp. 665–668
42. M.P. Cooke, P.D. Green, L.B. Josifovski, A. Vizinho: Robust automatic speech recognition with missing and uncertain acoustic data, Speech Commun. 34, 267–285 (2001)
43. S. Dharanipragada, M. Padmanabhan: A nonlinear unsupervised adaptation technique for speech recognition, Proc. Int. Conf. Spoken Lang. Process., Vol. IV (2000) pp. 556–559
44. R. Balchandran, R. Mammone: Non-parametric estimation and correction of non-linear distortion in speech systems, Proc. ICASSP, Vol. 2 (1998) pp. 749– 752
45. H. Erdogan, R. Sarikaya, Y. Gao, M. Picheny: Semantic structured language models, Proc. Int. Conf. Speech Lang. Process., Vol. 1 (2002) pp. 933– 936
46. R. Sarikaya, Y. Gao, M. Picheny: Word level confidence measurement using semantic features, Proc. ICASSP, Vol. 1 (2003) pp. 604–607
47. J. Bellegarda: Exploiting latent semantic information in statistical language modeling, Proc. IEEE 88(8), 1279–1296 (2000)
48. F. Jelinek, C. Chelba: Putting language into language modeling, Proc. Eurospeech, Vol. 1 (1999) pp. KN–1–KN–4
49. I. Gurevych, R. Malaka, R. Porzel, H.P. Zorn: Semantic coherence scoring using an ontology, Proc. HLT-NAACL (2003) pp. 88–95
50. A. Likhododev, Y. Gao: Direct models for phoneme recognition, Proc. ICASSP, Vol. 1 (2002) pp. 89–92
51. V. Vapnik: The support vector method, Proc. Int. Conf. Artif. Neural Networds (1997) pp. 263–271
52. S. Della Pietra, V. Della Pietra, J. Lafferty: Inducing features of random fields, IEEE Trans. Pattern Anal. Mach. Intell. 19(4), 380–393 (1997)
53. V. Venkataramani, W. Byrne: Lattice segmentation and support vector machines for large vocabulary continuous speech recognition, Proc. ICASSP, Vol. 1 (2005) pp. 817–820
54. L. Miller, M. Escabi, H. Read, C. Schreiner: Spatiotemporal receptive fields in the lemniscal auditory thalamus and cortex, J. Neurophysiol. 87, 516–527 (2001)
55. J.G. Fiscus: A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER), Proc. IEEE Workshop Autom. Speech Recognition Understanding, Santa Barbara (1997) pp. 347–355
56. Y. Freund, R.E. Schapire: Experiments with a new boosting algorithm, Proc. ICML (1996) pp. 148–156
57. O. Siohan, B. Ramabhadran, B. Kingsbury: Constructing ensembles of ASR systems using randomized decision trees, Proc. ICASSP, Vol. 1 (2005) pp. 197–200
58. IBM Research Communication Dept.: http://www. research.ibm.com/bluegene (2007)
59. IBM Research Communication Dept.: http://www. research.ibm.com/cell (2007)