This paper introduces bootstrap error estimation for automatic tuning of parameters in combined networks, applied as front-end preprocessors for a speech recognition system based on hidden Markov models. The method is evaluated on a large-vocabulary (10 000 words) continuous speech recognition task. Bootstrap estimates of minimum mean squared error allow selection of speaker normalization models improving recognition performance. The procedure allows a flexible strategy for dealing with inter-speaker variability without requiring an additional validation set. Recognition results are compared for linear, generalized radial basis functions and multi-layer perceptron network architectures.

Cesare, F., Diego, G., Trentin, E., & Stefano, M. (1997). Speaker normalization and model selection of combined neural networks. CONNECTION SCIENCE, 9(1), 31-50 [10.1080/095400997116720].

Speaker normalization and model selection of combined neural networks

TRENTIN, EDMONDO;
1997

Abstract

This paper introduces bootstrap error estimation for automatic tuning of parameters in combined networks, applied as front-end preprocessors for a speech recognition system based on hidden Markov models. The method is evaluated on a large-vocabulary (10 000 words) continuous speech recognition task. Bootstrap estimates of minimum mean squared error allow selection of speaker normalization models improving recognition performance. The procedure allows a flexible strategy for dealing with inter-speaker variability without requiring an additional validation set. Recognition results are compared for linear, generalized radial basis functions and multi-layer perceptron network architectures.
File in questo prodotto:
File Dimensione Formato  
01-FurlanelloGiulianiTrentinMerler.pdf

non disponibili

Tipologia: Post-print
Licenza: PUBBLICO - Pubblico con Copyright
Dimensione 366.06 kB
Formato Adobe PDF
366.06 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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: http://hdl.handle.net/11365/11709
 Attenzione

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