This paper deals with the effects of packet loss and voice data compression on vocal recognition over IP connections. One contribution of this paper consists in diagnosing most precisely the problems due to the compression and the packet losses for two different recognition tasks: the automatic speech recognition and speaker recognition. Another contribution corresponds to the proposal for recovering techniques in order to improve the robustness of systems under significant packet losses conditions. From the diagnosis, a more important degradation due to the compression on the speaker verification task was noted. The experimental results show that the techniques of interleaving based on the transmitter combined with the interpolation based on the receiver, prove to be the most efficient.
Packet Loss and Compression Effects on Vocal Recognition
01.09.2006
135378 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Speaker recognition using vocal source model
British Library Online Contents | 2014
|Performance of a volume holographic wavelet packet compression image recognition system [4551-17]
British Library Conference Proceedings | 2001
|Space adaptive wavelet packet image compression [2669-17]
British Library Conference Proceedings | 1996
|All-optical packet-header-recognition techniques
IEEE | 2002
|