DocumentCode :
3166184
Title :
Integration of beamforming and automatic speech recognition through propagation of the wiener posterior
Author :
Astudillo, Ramón Fernandez ; Abad, Alberto ; Neto, João Paulo da Silva
Author_Institution :
Spoken Language Lab., INESC-ID-Lisboa, Lisbon, Portugal
fYear :
2012
fDate :
25-30 March 2012
Firstpage :
4909
Lastpage :
4912
Abstract :
This paper details one of the front-end components of the system used at the PASCAL-CHiME multi-source robust automatic speech recognition (ASR) challenge 2011. The presented approach uses uncertainty propagation techniques to integrate conventional beamforming with automatic speech recognition. The paper addresses the derivation of a complex Gaussian posterior for the multi-channel Wiener and the delay and sum beamformer and introduces a new approach based on the propagation of the Wiener posterior through the resynthesizing process. Results on the PASCAL-CHiME task for this algorithms show that they consistently outperform conventional beamfomers with a minimal increase in computational complexity.
Keywords :
Gaussian processes; array signal processing; computational complexity; signal synthesis; speech recognition; stochastic processes; ASR; PASCAL-CHiME multisource robust automatic speech recognition; automatic speech recognition; beamforming; complex Gaussian posterior; computational complexity; front-end components; multichannel Wiener posterior propagation; uncertainty propagation techniques; Array signal processing; Delay; Noise; Robustness; Speech; Speech enhancement; Uncertainty; Beamforming; Observation Uncertainty; Robust ASR; Uncertainty Propagation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
ISSN :
1520-6149
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2012.6289020
Filename :
6289020
Link To Document :
بازگشت