Toward a practical implementation of exemplar-based noise robust ASR

European Signal Processing Conference

Volumn , Issue , 2011, Pages 1490-1494

  Gemmeke, Jort F ^a   Hurmalainen, Antti ^b   Virtanen, Tuomas ^b   Sun, Yang ^a  

^a RADBOUD UNIVERSITY NIJMEGEN   (Netherlands)

^b TAMPERE UNIVERSITY OF TECHNOLOGY   (Finland)

Author keywords

[No Author keywords available]

Indexed keywords

EXECUTION SPEED; LINEAR COMBINATIONS; NOISE TYPES; NOISY SPEECH; POSTERIOR LIKELIHOOD; PRACTICAL IMPLEMENTATION; RECOGNITION ACCURACY; ROBUST ASR; SPARSE REPRESENTATION;

PROGRAM PROCESSORS;

SIGNAL PROCESSING;

EID: 84863740422     PISSN: 22195491     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. L. Deng and H. Strik, "Structure-based and templatebased automatic speech recognition - comparing parametric and non-parametric approaches," in Proc. INTER-SPEECH, 2007, pp. 898-901.
2. Jort F. Gemmeke and Tuomas Virtanen, "Noise robust exemplar-based connected digit recognition," in Proc. ICASSP, 2010.
3. Tuomas Virtanen, Jort F. Gemmeke, and Antti Hurmalainen, "State-based labelling for a sparse representation of speech and its application to robust speech recognition," in Proc. Interspeech, 2010.
4. Pradeep Nagesh, Rahul Gowda, and Baoxin Li, "Fast GPU implementation of large scale dictionary and sparse representation based vision problems," in Proc. ICASSP, 2010, pp. 1570-1573.
5. Jort F. Gemmeke and Tuomas Virtanen, "Artificial and online acquired noise dictionaries for noise robust ASR," in Proc. Interspeech, 2010.
6. "GPUmat: GPU toolbox for MATLAB," Online: http://gp-you.org/, 2010.
7. Jort F. Gemmeke, L. ten Bosch, L.Boves, and B. Cranen,"Using sparse representations for exemplar based continuous digit recognition," in Proc. EUSIPCO, Glasgow, Scotland, August 24-28 2009, pp. 1755-1759.