Adaptive training aims at reducing the influence of speaker, channel and environment variability on the acoustic models. We describe an acoustic normalization approach to adaptive training. Phonetically irrelevant acoustic variability is reduced at the beginning of the training procedure w. r. t. a set of target models. The set of target models can be a set of HMMs or a Gaussian mixture model (GMM). CMLLR is applied to normalize the acoustic features. The normalized data contains less unwanted variability and is used to generate and train the recognition models. Employing a GMM as a target model leads to a text-independent procedure that can be embedded into the acoustic front-end. On a broadcast news transcription task we obtain relative reductions inWER of 7.8% in the first recognition pass over a conventionally trained system and of 3.4% in the second recognition pass over a SAT-trained system.

Adaptive Training Using Simple Target Models

Stemmer, Georg;Brugnara, Fabio;Giuliani, Diego
2005

Abstract

Adaptive training aims at reducing the influence of speaker, channel and environment variability on the acoustic models. We describe an acoustic normalization approach to adaptive training. Phonetically irrelevant acoustic variability is reduced at the beginning of the training procedure w. r. t. a set of target models. The set of target models can be a set of HMMs or a Gaussian mixture model (GMM). CMLLR is applied to normalize the acoustic features. The normalized data contains less unwanted variability and is used to generate and train the recognition models. Employing a GMM as a target model leads to a text-independent procedure that can be embedded into the acoustic front-end. On a broadcast news transcription task we obtain relative reductions inWER of 7.8% in the first recognition pass over a conventionally trained system and of 3.4% in the second recognition pass over a SAT-trained system.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/54011
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact