We investigated the usage for automatic speech recognition of different acoustic features, obtained from the output bitstream of a voice over IP codec. In particular, we analyzed the influence on recognition peformance, of both analysis rate and vector quantization of acoustic parameters introduced by the codec. Particular care has to be taken to train acoustic models at the reduced analysis rate employed by the codec: some related issues are discussed in the paper. We also used a model for simulating paket loss and we measurend the corresponding performance degradation. Experiments were carried out on both clean and noisy speech databases
Analysis of different acoustic front-ends for automatic voice over IP recognition
Falavigna, Giuseppe Daniele;Matassoni, Marco;Turchetti, Stefano
2003
Abstract
We investigated the usage for automatic speech recognition of different acoustic features, obtained from the output bitstream of a voice over IP codec. In particular, we analyzed the influence on recognition peformance, of both analysis rate and vector quantization of acoustic parameters introduced by the codec. Particular care has to be taken to train acoustic models at the reduced analysis rate employed by the codec: some related issues are discussed in the paper. We also used a model for simulating paket loss and we measurend the corresponding performance degradation. Experiments were carried out on both clean and noisy speech databasesI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
