| 469 | -- | 481 | Colin W. Wightman, Mari Ostendorf. Automatic labeling of prosodic patterns |
| 482 | -- | 489 | Lizhong Wu, Mahesan Niranjan, Frank Fallside. Fully vector-quantized neural network-based code-excited nonlinear predictive speech coding |
| 490 | -- | 506 | Nader Moayeri, David L. Neuhoff. Time-memory tradeoffs in vector quantizer codebook searching based on decision trees |
| 507 | -- | 520 | Li Deng, Michael Aksmanovic, Xiaodong Sun, C. F. Jeff Wu. Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states |
| 521 | -- | 530 | Stephen J. Elliott, Christopher C. Boucher. Interaction between multiple feedforward active control systems |
| 531 | -- | 536 | Mark M. Thomson, Bernard J. Guillemin. Design and performance of an algorithm for estimating vocal system parameters |
| 536 | -- | 539 | Gian Antonio Mian, Giuseppe Riccardi. A localization property of line spectrum frequencies |
| 539 | -- | 542 | W. Bastiaan Kleijn. On the periodicity of speech coded with linear-prediction based analysis by synthesis coders |
| 542 | -- | 543 | Carl D. Mitchell, Mary P. Harper, Leah H. Jamieson. Comments on "Reducing computation in HMM evaluation" |
| 544 | -- | 548 | Yan Ming Cheng, Douglas D. O'Shaughnessy, Paul Mermelstein. Statistical recovery of wideband speech from narrowband speech |
| 554 | -- | 566 | James W. Pitton, Les E. Atlas, Patrick J. Loughlin. Applications of positive time-frequency distributions to speech processing |
| 567 | -- | 577 | Jont B. Allen. How do humans process and recognize speech? |
| 578 | -- | 589 | Hynek Hermansky, Nelson Morgan. RASTA processing of speech |
| 590 | -- | 597 | Leonardo Neumeyer, Vassilios Digalakis, Mitchel Weintraub. Training issues and channel equalization techniques for the construction of telephone acoustic models using a high-quality speech corpus |
| 598 | -- | 614 | John H. L. Hansen. Morphological constrained feature enhancement with adaptive cepstral compensation (MCE-ACC) for speech recognition in noise and Lombard effect |
| 615 | -- | 621 | Stephen J. Young, Philip C. Woodland, William J. Byrne. Spontaneous speech recognition for the credit card corpus using the HTK toolkit |
| 622 | -- | 629 | Qiguang Lin, Ea-Ee Jan, James L. Flanagan. Microphone arrays and speaker identification |
| 630 | -- | 638 | Khaled T. Assaleh, Richard J. Mammone. New LP-derived features for speaker identification |
| 639 | -- | 643 | Douglas A. Reynolds. Experimental evaluation of features for robust speaker identification |