Robust acoustic segmentation has become a critical issue in order to apply speech recognition to audio streams with variable acoustic content, e.g. radio programs. Many techniques in the literature base segmentation on statistical model selection, by applying the Bayesan Information Criterion. This work reviews alternative model selection criteria and presents comparative experiments both under controlled conditions and on a broadcast news corpus
Model Selection Criteria for Acoustic Segmentation
Cettolo, Mauro;Federico, Marcello
2000-01-01
Abstract
Robust acoustic segmentation has become a critical issue in order to apply speech recognition to audio streams with variable acoustic content, e.g. radio programs. Many techniques in the literature base segmentation on statistical model selection, by applying the Bayesan Information Criterion. This work reviews alternative model selection criteria and presents comparative experiments both under controlled conditions and on a broadcast news corpusFile 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.
