Prosody and Speech Recognition
Prosody and Speech Recognition
Large-vocabulary speaker-independent continuous speech recognition: the sphinx system
Large-vocabulary speaker-independent continuous speech recognition: the sphinx system
Improved acoustic modeling for speaker independent large vocabulary continuous speech recognition
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Exploiting variable-width features in large vocabulary speech recognition
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
| Hi-index | 0.00 |
Stress is an important feature for speech recognition. Firstly, the acoustic realisation of a stressed phone tends to be rather different from its unstressed counterpart. Secondly stress may be a distinctive feature for lexical classification, as is the case for English. In most cases stress is important for understanding the meaning of an utterance, and is thus related to syntax and semantics. In this proposal, we focus on the acoustic modelling of stressed phones, and more particularly of stressed vowels. The recognition system is based on discrete HMM phone models, and has been developped within the European ESPRIT-POLYGLOT 2041 project. The influence of the stress feature on acoustic modelling is being assessed on two different continuous speech databases in two different languages (French and American-English), as the effect of stress on the acoustic evidence may be language-dependent. First results concerning phonetic and lexical evaluations are given hereafter.