Index for 4pSC

• 4pSC1. Dynamic auditory representations and statistical speech recognition.
• 4pSC2. A robust speech recognition algorithm.
• 4pSC3. Robust speech parameter based on a psychoacoustical rule-base model.
• 4pSC4. Vowel identification from harmonic contours.
• 4pSC5. Robust speech recognition using singular value decomposition based speech enhancement.
• 4pSC6. Effects of noise masking on the identification of fricative noise frequency.
• 4pSC7. Word boundary detection under noise by using an adaptive noise canceler.
• 4pSC8. Recognition of first words of isolated spoken word pairs with ambiguous word boundaries.
• 4pSC9. Phonetically balanced cepstrum mean normalization for telephone speech.
• 4pSC10. Robust word recognition in an automobile by using cepstral normalization and an improved acoustic model.
• 4pSC11. Affine transformation-based feature normalization for speaker-independent speech recognition.
• 4pSC12. Noisy speech recognition using HMM-based cepstral parameter generation and compensation.
• 4pSC13. Isolated word recognition in a noisy environment.
• 4pSC14. Investigation of subband-cross-correlation analysis for speech recognition under noisy conditions.
• 4pSC15. Speech recognition based on subword units.
• 4pSC16. Comparison of the effect of homophones on speechreading between Japanese and English.
• 4pSC17. In search of an invariant representation for speech: The modulation spectrogram.
• 4pSC18. Phoneme recognition using reference patterns constructed with discriminative training and DP matching.
• 4pSC19. Feature and model compensation for robust speech recognition.
• 4pSC20. Beyond a ``short-term'' analysis of speech.
• 4pSC21. Evaluation of a rapid environment adaptation algorithm in adverse environments.
• 4pSC22. Compensation for speech recognition in degraded acoustical environments.
• 4pSC23. Hands-free speech recognition by a microphone array and HMM composition.
• 4pSC24. Multisensor-based speech processing for robust speech recognition.
• 4pSC25. Model-based unsupervised instantaneous speaker adaptation.
• 4pSC26. Fast speaker-independent acoustic modeling and speaker adaptation.