Second European Conference on Speech Communication and Technology

Genova, Italy
September 24-26, 1991


A Comparative Study on Hybrid Acoustic Phonetic Decoders Based on Artificial Neural Networks

Yoshua Bengio, Renato De Mori, Giovanni Flammia, Ralf Kompe

School of Computer Science, McGill University, Montreal, Qc, Canada

In this paper we compare two hybrid acoustic-phonetic decoders based on Artificial Neural Networks (ANN). We evaluate them on the task of recognizing stop phones in continuous speech independently from the speaker. ANNs are well suited to perform detailed phonetic distinctions. In general, techniques based on Dynamic Programming (DP), in particular Hidden Markov Models (HMMs), have proven to be successful at modeling the temporal structure of the speech signal. In the approach described here, the ANN outputs constitute the sequence of observation vectors for the HMM. An algorithm is proposed for global optimization of all the parameters of the ANN/HMM decoder. Comparative experiments using this ANN/HMM hybrid decoder and another ANN-DP hybrid are reported for the TIMIT database.

Full Paper

Bibliographic reference.  Bengio, Yoshua / Mori, Renato De / Flammia, Giovanni / Kompe, Ralf (1991): "A comparative study on hybrid acoustic phonetic decoders based on artificial neural networks", In EUROSPEECH-1991, 1007-1010.