Robust speech recognition for multiple topological scenarios of the GSM mobile phone system
Authors:
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 101-104
Abstract
This paper deals with robust speech recognition in the GSM mobile environment. Our focus is on the voice degradation due to the losses in the GSM coding scheme. Thus, we initially propose an experimental framework of network topologies that consists of various coding-decoding systems placed in tandem. After measuring the recognition performance for each of these network scenarios, we try to increase recognition accuracy by using feature compensation and model adaptation algorithms. We first compare the different methods for all the network topologies assuming the topology is known. We then investigate the more realistic case, in which we don't know the network topology the voice has passed through. The results show that robustness can be achieved even in this case.Keywords
This publication has 6 references indexed in Scilit:
- Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer2002
- Voice quality of interconnected North-American cellular, European cellular, and public switched telephone networks2002
- Speaker adaptation using combined transformation and Bayesian methodsIEEE Transactions on Speech and Audio Processing, 1996
- A comparative study of speaker adaptation techniques1995
- Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov modelsComputer Speech & Language, 1995
- Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques1993