Kunio Tanabe
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kunio Tanabe has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Oystein Birkenes
The Institute of Statistical Mathematics, Tokyo, Japan; Department of Electronics and Telecommunications, NTNU, Trondheim, Norway
2 shared publications - Tomoko Matsui
The Institute of Statistical Mathematics, Tachikawa, Japan
2 shared publications - Tor Andre Myrvoll
The Institute of Statistical Mathematics, Tokyo, Japan; Department of Electronics and Telecommunications, NTNU, Trondheim, Norway
2 shared publications
Latest Publications
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-449-449
N-Best Rescoring for Speech Recognition using Penalized Logistic Regression Machines with Garbage Class
State-of-the-art pattern recognition approaches like neural networks or kernel methods have only had limited success in speech recognition. The difficulties often encountered include the varying lengths of speech signals as well as how to deal with sequences of labels (e.g., digit strings) and unknown segmentation. In this paper we present a combined hidden Markov model (HMM) and penalized logistic regression machine (PLRM) approach to continuous speech recognition that can cope with both of these difficulties. The key ingredients of our approach are N-best rescoring and PLRM with garbage class. Experiments on the Aurora2 connected digits database show significant increase in recognition accuracy relative to a purely HMM-based system.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-449-449
N-Best Rescoring for Speech Recognition using Penalized Logistic Regression Machines with Garbage Class
State-of-the-art pattern recognition approaches like neural networks or kernel methods have only had limited success in speech recognition. The difficulties often encountered include the varying lengths of speech signals as well as how to deal with sequences of labels (e.g., digit strings) and unknown segmentation. In this paper we present a combined hidden Markov model (HMM) and penalized logistic regression machine (PLRM) approach to continuous speech recognition that can cope with both of these difficulties. The key ingredients of our approach are N-best rescoring and PLRM with garbage class. Experiments on the Aurora2 connected digits database show significant increase in recognition accuracy relative to a purely HMM-based system.
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 110-113
Continuous Speech Recognition with Penalized Logistic Regression Machines
Penalized logistic regression machines (PLRMs) have recently been shown to give good performance on isolated word speech re cognition. In this paper, we extend this framework to continuous speech recognition. We present two approaches that both make use of the output from an HMM Viterbi recognizer. The first approach performs probabilistic prediction with PLRM on the segments obtained from the HMM Viterbi recognizer. The resulting subwords and subword probabilities are combined to form a sentence and a sentence probability, respectively. In the second approach, an N-best list generated by the HMM Viterbi recognizer is rescored using PLRM. Experiments on the Aurora2 connected digits database show that both approaches outperform the baseline HMM Viterbi recognizer
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 110-113
Continuous Speech Recognition with Penalized Logistic Regression Machines
Penalized logistic regression machines (PLRMs) have recently been shown to give good performance on isolated word speech re cognition. In this paper, we extend this framework to continuous speech recognition. We present two approaches that both make use of the output from an HMM Viterbi recognizer. The first approach performs probabilistic prediction with PLRM on the segments obtained from the HMM Viterbi recognizer. The resulting subwords and subword probabilities are combined to form a sentence and a sentence probability, respectively. In the second approach, an N-best list generated by the HMM Viterbi recognizer is rescored using PLRM. Experiments on the Aurora2 connected digits database show that both approaches outperform the baseline HMM Viterbi recognizer