University Homepage School Homepage School Contacts School Search

References for ASR

Textbook

• Daniel Jurafsky and James H. Martin (2008). Speech and Language Processing, Pearson Education (2nd edition). (Errata) [chapters 6, 9, 10]

Wikipedia

Wikipedia coverage of most ASR topics is very poor. However the following entries on same basic pattern recognition and density estimation topics are OK:

• Normal distribution
• Maximum Likelihood Estimation (MLE)
• GMM
• EM algorithm

Review and Tutorial Articles

• S Renals and T Hain (2010). Speech Recognition, to appear in Computational Linguistics and Natural Language Processing Handbook, A Clark, C Fox and S Lappin (eds.), Blackwells.
• MJF Gales and SJ Young (2007). The Application of Hidden Markov Models in Speech Recognition, Foundations and Trends in Signal Processing, 1 (3), 195-304.
• S Young (1996). A review of large-vocabulary continuous-speech recognition, IEEE Signal Processing Magazine 13 (5), 45--57.
• J-L Gauvain and L Lamel (2000). Large-vocabulary continuous speech recognition: advances and applications, Proceedings of the IEEE, 88 (8), 1181-1200.
• PC Woodland (2002). The development of the HTK Broadcast News transcription system: An overview, Speech Communication, 37(1--2), 47-67.
• S Young (2008). HMMs and Related Speech Recognition Technologies, in Springer Handbook of Speech Processing, J Benesty, MM Sondhi and Y Huang (eds), chapter 27, 539--557.

HMM

• L Rabiner and B Juang (1986), An introduction to hidden Markov models IEEE ASSP Magazine, 3 (1), 4--16.
• JR Bellegarda and D Nahamoo (1990). Tied mixture continuous parameter modeling for speech recognition, IEEE Trans ASSP, 38 (12), 2033-2045.
• XD Huang (1992). Phoneme classification using semicontinuous hidden Markov models , IEEE Trans Signal Processing, 40 (5), 1062-1067.
• SJ Young and PC Woodland (1994). State clustering in hidden Markov model-based continuous speech recognition, Computer Speech and Language ,4, 369-383.

Context-dependent phone models

• R. Schwartz, Y. Chow, O. Kimball, S. Roucos, M. Krasner and J. Makhoul (1985). Context-dependent modeling for acoustic-phonetic recognition of continuous speech, Proc IEEE ICASSP-85, 1205-1208.
• K-F Lee (1990). Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition, IEEE Trans on ASSP, 38(4), 599-609.
• LR Bahl, PV de Souza, PS Gopalakrishnan, D Nahamoo and MA Picheny (1991). Context Dependent Modeling of Phones in Continuous Speech Using Decision Trees, Proc DARPA Speech and Natural Language Processing Workshop, 264-270.
• S Young, J Odell and P Woodland (1994). Tree-based state tying for high accuracy acoustic modelling, Proc HLT Workshop, 307-312.

Pronunciation modelling

• E. Fosler-Lussier (2003). A tutorial on pronunciation modeling for large vocabulary speech recognition, in S. Renals and G. Grefenstette (eds) Text and Speech Triggered Information Access, LNAI 2705, Springer.
• T. Hain (2002). Implicit pronunciation modelling in ASR, in Proc. ISCA Workshop on Pronunciation Modeling and Lexicon Adaptation (PMLA--2002), pp. 129-134.

Language modelling

• C. Manning and H. Schutze (1999). Foundations of Statistical Language Processing, MIT Press. (Chapter 6)
• Y. Gotoh and S. Renals (2003). Language modelling, in S. Renals and G. Grefenstette (eds) Text and Speech Triggered Information Access, LNAI 2705, Springer.
• F. Jelinek (1991). Up from trigrams! The struggle for improved language models, Proc. Eurospeech.
• C. Chelba and F. Jelinek (2000). Structured language modeling, Computer Speech and Language, 14:283-332.
• J. Goodman (2001). A bit of progress in language modeling, Computer Speech and Language, 15:403-434.

Search

• X Aubert (2002), An overview of decoding techniques for large vocabulary continuous speech recognition, Computer Speech and Language , 16:89-114.
• M Mohri, F Pereira and M Riley (2002). Weighted finite-state transducers in speech recognition, Computer Speech and Language , 16:69-88.
• D Moore et al (2006). Juicer: A WFST speech decoder, in Proc MLMI-06, Springer LNCS 4299, 285-296.

Speaker Adaptation

• P Woodland (2001). Speaker adaptation for continuous density HMMs: A review, Proceedings of the ISCA workshop on adaptation methods for speech recognition, 11-19.
• M Gales and P Woodland (1996). Mean and variance adaptation within the MLLR framework, Computer Speech and Language, 10:249-264.
• M Gales (1998). Maximum likelihood linear transformations for HMM-based speech recognition , Computer Speech and Language, 12:75-98.
• M Gales (2000). Cluster adaptive training of hidden Markov models, IEEE Trans Speech and Audio Processing, 8:417-428.
• R Kuhn, JC Junqua, P Nguyen and N Niedzielski (2000). Rapid speaker adaptation in eigenvoice space, IEEE Trans Speech and Audio Processing, 8:695-707
• G Garau, S Renals and T Hain (2005). Applying vocal tract length normalization to meeting recordings, Proc Interspeech'05

Large Vocabulary Systems

• P Woodland (2002). The development of the HTK Broadcast News transcription system: An overview, Speech Communication, 37(1-2):47-67.
• SF Chen et al (2006). Advances in speech transcription at IBM under the DARPA EARS program, IEEE Trans Speech and Audio Processing, 14(5):1596-1608.
• S. Renals, T. Hain and H. Bourlard (2007). Recognition and understanding of meetings: The AMI and AMIDA projects, Proc. IEEE ASRU.
• T. Hain et al (2005). The development of the AMI system for the transcription of speech in meetings. Proc. MLMI '05

Discriminative Training

• A Nadas (1983). A decision theoretic formulation of a training problem in speech recognition and a comparison of training by unconditional versus conditional maximum likelihood, Proc IEEE Trans ASSP, 31(4):814-817.
• L Bahl, P Brown, P de Souza and R Mercer (1986). Maximum mutual information estimation of hidden Markov model parameters for speech recognition, Proc IEEE ICASSP '86
• Y Normandin and SD Morgera (1992). An improved MMIE training algorithm for speaker-independent, small vocabulary, continuous speech recognition, Proc IEEE ICASSP '92
• PC Woodland and D Povey (2002). Large scale discriminative training of hidden Markov models for speech recognition, Computer Speech and Language, 16(1):25-47.
• D. Povey (2003). Discriminative Training for Large Vocabulary Speech Recognition, PhD thesis, University of Cambridge.

Robustness

• J Droppo and A Acero (2008). Environmental Robustness, in Springer Handbook of Speech Processing, J Benesty, MM Sondhi and Y Huang (eds), chapter 33, 653--680.

(Deep) neural networks

• N Morgan and H Bourlard (May 1995). Continuous speech recognition: An introduction to the hybrid HMM/connectionist approach, IEEE Signal Processing Magazine, 12(3), 24-42.
• N Morgan et al (Sep 2005). Pushing the envelope - aside, IEEE Signal Processing Magazine, 22(5), 81-88. %
• F Grezl and P Fousek (2008). Optimizing bottleneck features for LVCSR, Proc ICASSP-2008.
• G Hinton et al (Nov 2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, IEEE Signal Processing Magazine, 29(6), 82--97.

Transcribing TED data

• M. Federico et al (2012). Overview of the IWSLT 2012 evaluation campaign, in Proc. IWSLT-2012.
• H. Yamamoto et al (2012). The NICT ASR system for the IWSLT2012, in Proc. IWSLT-2012.
• E. Hasler et al (2012). The UEDIN systems for the IWSLT 2012 evaluation, in Proc. IWSLT-2012.
• P. Bell et al (2013). Multi-level adaptive networks in tandem and hybrid ASR systems, in Proc. ICASSP-2013.
• T. Mikolov et al (2010). Recurrent neural network based language model, in Proc. Interspeech-2010.

---

Introductory texts (now getting rather old)

• Comp.Speech FAQ
• Speech Analysis
• "Spoken Language Input" , which is the first chapter of Survey of the State of the Art in Human Language Technology

Language Models

• Statistical Methods in Computational Linguistics by Mark Gawron @ San Diego State Univ.
• SRILM Manual Pages
• Good-Turing Smoothing Without Tears by William A. Gale @ ATT Bell Lab, 1994.
• A Survey of Smoothing Techniques for ME Models by Stanley F. Chen, Ronald Rosenfeld, IEEE Trans SAP, Vol.8, No.1, January 2000.
• A study of smoothing methods for language models applied to information retrieval by Chengxiang Zhai and John Lafferty @ CMU, ACM Trans on Information Systems, Vol. 22, Issue 2, pp.179-214, April 2004.

Decoding / Search

• The N-Best algorithm: an efficient procedure for finding top N sentence hypotheses by Yen-Lu Chow and Richard Schwartz @ BBN,

Speaker Recognition

• Speaker Recognition by Sadaoki Furui in Survey of the State of the Art in Human Language Technology (1996)
• NIST Speaker Recognition Evaluation Chronicles by Mark Przybocki and Alvin Martin, 2004.
• Automatci Speaker Recognition - Recent progress, Current applications, and Future trends by D. A. Raynolds and L. P. Heck, at AASS2000
• Speaker Recognition, a tutorial by J.C. Campbell, 1997, Proceedings of IEEE, vol.85, No.9, pp.1437-1562, 1997 September.
• Odyssey - Speaker and Language Characterization Interest Group

Audio Signal Processing

• Gentle introduction for Microphone Arrays

History

• Automatic Speech Recognition - A brief history of technology development by B.H. Juang and L.R Rabiner
• NIST's Benchmark test history
• Speech
• Learning from the experience of building automatic speech recognition systems by Mark Huckvale
• Challenges in Speech Recognition by L.R. Rabiner (pdf) (ppt)

Other topics

• Prosody modeling for automatic speech recognition and modeling by E Shriberg and A Stolcke, Mathematical Foundations of Speech and Language Processing, 2004.
• Audio-visual Automatic Speech Recognition: An Overview by G. Potamianos, C. Neti, J. Luettin, and I. Matthews, In: Issues in Visual and Audio-Visual Speech Processing, G. Bailly, E. Vatikiotis-Bateson, and P. Perrier (Eds.), MIT Press (In Press), 2004.