5th International Conference on Spoken Language Processing
Speech coding affects speech recognition performance, with recognition accuracy deteriorating as the coded bit rate decreases. Virtually all systems that recognize coded speech reconstruct the speech waveform from the coded parameters, and then perform recognition (after possible noise and/or channel compensation) using conventional techniques. In this paper we compare the recognition accuracy of coded speech obtained by reconstructing the speech waveform with the speech recognition accuracy obtained when using cepstral features derived from the coding parameters. We focus our efforts on speech that has been coded using the 13-kbps full-rate GSM codec, a Regular Pulse Excited Long Term Prediction (RPE-LTP) codec. The GSM codec develops separate representations for the linear prediction (LPC) filter and the residual signal components of the coded speech. We measure the effects of quantization and coding on the accuracy with which these parameters are represented, and present two different methods for recombining them for speech recognition purposes. We observe that by selectively combining the cepstral streams repre senting the LPC parameters and the residual signal it is possible to obtain recognition accuracy directly from the coded parameters that equals or exceeds the recognition accuracy obtained from the reconstructed waveforms.
Bibliographic reference. Huerta, Juan M. / Stern, Richard M. (1998): "Speech recognition from GSM codec parameters", In ICSLP-1998, paper 0626.