21 search results - page 3 / 5 » Combining Spectral Representations for Large-Vocabulary Cont... |
ICASSP
2010
IEEE
13 years 4 months ago
2010
IEEE
Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectr...
ICASSP
2011
IEEE
12 years 10 months ago
2011
IEEE
The acceleration of acoustic likelihood calculation has been an important research issue for developing practical speech recognition systems. And there are various specification ...
ICASSP
2010
IEEE
13 years 6 months ago
2010
IEEE
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
SIGIR
2006
ACM
14 years 5 days ago
2006
ACM
We are interested in retrieving information from conversational speech corpora, such as call-center data. This data comprises spontaneous speech conversations with low recording q...
ICASSP
2011
IEEE
12 years 10 months ago
2011
IEEE
This paper presents a discriminative training (DT) approach to irrelevant variability normalization (IVN) based training of feature transforms and hidden Markov models for large v...