论文信息 - Weighted linear prediction for speech analysis in noisy conditions

Weighted linear prediction for speech analysis in noisy conditions

1 k p; where E = X n (s n p X k=1 a k s n k ) 2 I WLP is a generalization of LP, introducing temporal weighting of the squared prediction error [2]: E = X n (s n p X k=1 a k s n k ) 2 W n IW n is the weighting function I For constant W n , WLP becomes identical to LP! Stabilized Weighted Linear Prediction (SWLP)

Paavo Alku | Mikko Kurimo | Jouni Pohjalainen | Kalle J. Palomäki | Heikki Kallasjoki

[1] Paavo Alku,et al. Stabilised weighted linear prediction , 2009, Speech Commun..

[2] Yves Kamp,et al. Robust signal selection for linear prediction analysis of voiced speech , 1993, Speech Commun..

[3] J. Makhoul,et al. Linear prediction: A tutorial review , 1975, Proceedings of the IEEE.

[4] Mikko Kurimo,et al. Unlimited vocabulary speech recognition with morph language models applied to Finnish , 2006, Comput. Speech Lang..

[5] Vesa Siivola,et al. Growing an n-gram language model , 2005, INTERSPEECH.

[6] Krzysztof Marasek,et al. SPEECON – Speech Databases for Consumer Devices: Database Specification and Validation , 2002, LREC.

[7] Alex Acero,et al. Spoken Language Processing , 2001 .

[8] Janne Pylkkönen. AN EFFICIENT ONE-PASS DECODER FOR FINNISH LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION , .

[9] Hugo Fastl,et al. Psychoacoustics: Facts and Models , 1990 .

[10] Paavo Alku,et al. Noise Robust LVCSR feature extraction based on stabilized weighted linear prediction , 2009 .

[11] Mikko Kurimo,et al. Duration modeling techniques for continuous speech recognition , 2004, INTERSPEECH.