HMM/MLP hybrid speech recognizer for the Portuguese telephone SpeechDat corpus

Authors:
Astrid Hagen;João P. Neto
Affiliations:
Spoken Language Systems Lab, INESC-ID, Lisboa, Portugal;Spoken Language Systems Lab, INESC-ID, Lisboa, Portugal and Instituto Superior Técnico, Portugal
Venue:
PROPOR'03 Proceedings of the 6th international conference on Computational processing of the Portuguese language
Year:
2003

Citing 3
Cited 0

Connectionist Speech Recognition: A Hybrid Approach

Connectionist Speech Recognition: A Hybrid Approach
The Modulation Spectrogram: In Pursuit of an Invariant Representation of Speech

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 3 - Volume 3
European Speech Databases for Telephone Applications

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 3 - Volume 3

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article, we describe an automatic speech recognizer developed for Portuguese telephone speech. For this, we employed the Portuguese SpeechDat database which will be described in detail, giving its recording conditions, speaker characteristics and contents categories. The automatic recognizer is a state-of-the-art HMM/MLP hybrid system employing different kinds of robust acoustic features. Training and testing was carried out on the clean digits and numbers part of the database. The recognition results show competitive performance to similar systems developed for other languages.