- The 4th International Conference on Spoken Language Processing, Philadelphia, PA, USA, October 3-6, 1996. ISCA 1996
- Anne Cutler:
The comparative study of spoken-language processing.
- James L. Flanagan:
Natural communication with machines - progress and challenge.
- Alette P. Haveman:
Effects of frequency on the auditory perception of open- versus closed-class words.
- Byunggon Yang:
Perceptual contrast in the Korean and English vowel system normalized.
- Maria-Barbara Wesenick:
Automatic generation of German pronunciation variants.
- James J. Mahshie:
Feedback considerations for speech training systems.
- Anne-Marie Öster:
Clinical applications of computer-based speech training for children with hearing impairment.
- D. R. Campbell:
Sub-band adaptive speech enhancement for hearing aids.
- Katsuhiko Shirai:
Modeling of spoken dialogue with and without visual information.
- Marcello Federico:
Bayesian estimation methods for n-gram language model adaptation.
- Petra Geutner:
Introducing linguistic constraints into statistical language modeling.
- Don X. Sun:
Feature dimension reduction using reduced-rank maximum likelihood estimation for hidden Markov models.
- Kai Hübener:
Using multi-level segmentation coefficients to improve HMM speech recognition.
- Ben Milner:
Inclusion of temporal information into features for speech recognition.
- Andrzej Drygajlo:
New fast wavelet packet transform algorithms for frame synchronized speech processing.
- Gavin C. Cawley:
An improved vector quantization algorithm for speech transmission over noisy channels.
- Minoru Kohata:
An application of recurrent neural networks to low bit rate speech coding.
- Ann K. Syrdal:
Acoustic variability in spontaneous conversational speech of american English talkers.
- Kiyoko Yoneyama:
Segmentation strategies for spoken language recognition: evidence from semi-bilingual Japanese speakers of English.
- Reinhard Kneser:
Statistical language modeling using a variable context length.
- Finn Tore Johansen:
A comparison of hybrid HMM architectures using global discriminative training.
- Gordon Ramsay:
A non-linear filtering approach to stochastic training of the articulatory-acoustic mapping using the EM algorithm.