This paper reports on experiments of porting the ITC-irst Italian broadcast news recognition system to two spontaneous dialogue domains. Porting was investigated by applying state-of-the-art adaptation methods on acoustic and language models, and by evaluating the trade-off between performance and required amount of task specific annotated data. The use of different levels of supervision for acoustic model adaptation was also studied. By employing two hours of manually annotated speech, word error rates of 26.0% and 28.4% were achieved by the adapted systems These results are to be compared with the performance of two domain specific baseline systems, 22.6% and 21.2% respectively, which were developed on much more training data. Finally, a robust method is presented that allows to tune the insertion of spontaneous speech phenomena by the speech decoder
Cross-Task Portability of a Broadcast News Speech Recognition System
Bertoldi, Nicola;Brugnara, Fabio;Cettolo, Mauro;Federico, Marcello;Giuliani, Diego
2002-01-01
Abstract
This paper reports on experiments of porting the ITC-irst Italian broadcast news recognition system to two spontaneous dialogue domains. Porting was investigated by applying state-of-the-art adaptation methods on acoustic and language models, and by evaluating the trade-off between performance and required amount of task specific annotated data. The use of different levels of supervision for acoustic model adaptation was also studied. By employing two hours of manually annotated speech, word error rates of 26.0% and 28.4% were achieved by the adapted systems These results are to be compared with the performance of two domain specific baseline systems, 22.6% and 21.2% respectively, which were developed on much more training data. Finally, a robust method is presented that allows to tune the insertion of spontaneous speech phenomena by the speech decoderI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
