Avoiding distortions due to speech coding and transmission errors in GSM ASR tasks

We have extended our previous research on a new approach to automatic speech recognition (ASR) in the GSM environment. Instead of recognizing from the decoded speech signal, our system works from the digital speech representation used by the GSM encoder. We have compared the performance of a conventional system and the one we propose on a speaker independent, isolated-digit ASR task. For the half and full-rate GSM codecs, from our results, we conclude that the proposed approach is much more effective in coping with the coding distortion and transmission errors. Furthermore, in clean speech conditions, our approach does not impoverish the recognition performance, even recognizing from GSM digital speech, in comparison with a conventional system working on unencoded speech