Comparison and combination of features in a hybrid HMM/MLP and a HMM/GMM speech recognition system

IEEE Transactions on Speech and Audio Processing

Volumn 13, Issue 1, 2005, Pages 14-22

  Pujol, Pere ^a   Pol, Susagna ^a   Nadeu, Climent ^a   Hagen, Astrid ^b   Bourlard, Hervé ^c  

^a UNIVERSITAT POLITÈCNICA DE CATALUNYA   (Spain)

^b INESC ID   (Portugal)

^c IDIAP RESEARCH INSTITUTE   (Switzerland)

Author keywords

Frequency filtering (FF); MLP; Multistream; Product rule; Relative spectra (Rasta); Robustness

Indexed keywords

ERROR ANALYSIS; LINEAR SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; ROBUSTNESS (CONTROL SYSTEMS);

FREQUENCY FILTERING; PRODUCT RULE; RELATIVE SPECTRA;

SPEECH RECOGNITION;

EID: 11144222882     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2004.834466     Document Type: Article

References (13)

1. C. Nadeu, J. Hemando, and M. Gorricho, "On the decorrelation of filterbank energies for speech recognition," in Proc. Eurospeech, 1995, pp. 1381-1384.
2. K. K. Paliwal, "Decorrelated and liftered filter-bank energies for robust speech recognition," in Proc. Eurospeech, 1999, pp. 85-88.
3. C. Nadeu, D. Macho, and J. Hernando, "Frequency and time filtering of filter-bank energies for Robust HMM speech recognition," Speech Commun., vol. 34, pp. 93-114, 2001.
4. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. Acoust. Soc. Am., vol. 87, no. 4, pp. 1738-1752, 1990.
5. H. Hermansky and N. Morgan, "Rasta processing of speech," IEEE Trans. Speech Audio Processing, vol. 2, no. 4, pp. 578-589, Oct. 1994.
6. A. Hagen, "Robust speech recognition based on multi-stream processing," Ph.D. dissertation, Lab. d'lntell. Artif. Perceptive, École Polytechnique Fédérale, Lausanne, Switzerland, 2001.
7. D. H. Klatt, "Prediction of perceived phonetic distance from critical band spectra: A first step," in Proc. ICASSP, 1982, pp. 1278-1281.
8. H. Bourlard and N. Morgan, Connectionist Speech Recognition. A Hybrid Approach. Norwell, MA: Kluwer, 1994.
9. R. A. Cole, M. Noel, T. Lander, and T. Durham, "New telephone speech corpora at CSLU," in Proc. Eurospeech, vol. 1, 1995, pp. 821-824.
10. A. Varga, H. J. M. Steeneken, M. Tomlison, and D. Jones. (1992) The NOISEX-92 Study on the Effect of Additive Noise on Automatic Speech Recognition. [CD-ROM] Documentation included in the NOISEX-92 CD-ROM Set
11. D. Ellis and M. J. R. Gomez, "Investigations into tandem acoustic modeling for the aurora task," in Proc. Eurospeech, vol. 1, 2001, pp. 189-192.
12. K. Kirchhoff and J. Bilmes, "Combination and joint training of acoustic classifiers for speech recognition," in Proc. ISCA ITRW Workshop Automatic Speech Recognition (ASA), 2000, pp. 17-23.
13. J. Koehler, N. Morgan, H. Hermansky, H. G. Guenter, and G. Tong, "Integrating rasta-PLP into speech recognition," IEEE Trans. Signal Process., vol. 42, no. 1, pp. 421-424, Jan. 1994.