Context-dependent MLPs for LVCSR: TANDEM, hybrid or both?

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 1, Issue , 2012, Pages 18-21

  Tüske, Zoltán ^a   Sundermeyer, Martin ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

ASR; Bottle neck; GMM; HMM; Hybrid; MLP; TANDEM

Indexed keywords

ASR; BOTTLE-NECK; GMM; HMM; HYBRID; MLP; TANDEM;

CONTINUOUS SPEECH RECOGNITION;

BOTTLES;

EID: 84878403164     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. H. Hermansky et al., "Tandem connectionist feature extraction for conventional HMM systems," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 3, 2000, pp. 1635-1638.
2. F. Grézl et al., "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2007, pp. 757-760.
3. H. A. Bourlard and N. Morgan, Connectionist Speech Recognition: A Hybrid Approach. Norwell, MA, USA: Kluwer Academic Publishers, 1993.
4. F. Seide et al., "Conversational Speech Transcription Using Context-Dependent Deep Neural Networks," in Proc of Interspeech, 2011, pp. 437-440.
5. A. Mohamed et al., "Acoustic Modeling Using Deep Belief Networks," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 14-22, jan. 2012.
6. F. Seide et al., "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in Proc of IEEE Automatic Speech Recognition and Understanding Workshop, 2011, pp. 24-29.
7. C. Plahl et al., "Improved Pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines," in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Mar. 2012.
8. T. N. Sainath et al., "Making Deep Belief Networks Effective for Large Vocabulary Continuous Speech Recognition," in Proc of IEEE Automatic Speech Recognition and Understanding Workshop, 2011, pp. 30-35.
9. F. Valente et al., "A comparative large scale study of MLP features for Mandarin ASR," in Proc. of Interspeech, 2010, pp. 2630-2633.
10. M. Sundermeyer et al., "The RWTH 2010 QUAERO ASR Evaluation System for English, French, and German," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2011, pp. 2212-2215.
11. Z. Tüske et al., "Comparison and combination of different CRBE based MLP features for LVCSR," in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Mar. 2012.
12. G. Stemmer et al., "Adaptive training using simple target models," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 1, 2005, pp. 997-1000.
13. M. Sundermeyer et al., "On the Estimation of Discount Parameters for Language Model Smoothing," in Proc. of Interspeech, 2011, pp. 1433-1436.
14. D. Rybach et al., "RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit," in Proc of IEEE Automatic Speech Recognition and Understanding Workshop, 2011.