Selection of Shared-State Hidden Markov Model Structure Using Bayesian Criterion(<Special Section>the 2003 IEICE Excellent Paper Award)
スポンサーリンク
概要
- 論文の詳細を見る
A Shared-State Hidden Markov Model (SS-HMM) has been widely used as an acoustic model in speech recognition. In this paper, we propose a method for constructing SS-HMMs within a practical Bayesian framework. Our method derives the Bayesian model selection criterion for the SS-HMM based on the variational Bayesian approach. The appropriate phonetic decision tree structure of the SS-HMM is found by using the Bayesian criterion. Unlike the conventional asymptotic criteria, this criterion is applicable even in the case of an insufficient amount of training data. The experimental results on isolated word recognition demonstrate that the proposed method does not require the tuning parameter that must be tuned according to the amount of training data, and is useful for selecting the appropriate SS-HMM structure for practical use.
- 社団法人電子情報通信学会の論文
- 2005-01-01
著者
-
Minami Yasuhiro
Ntt Communication Science Laboratories Ntt Corporation
-
Nakamura Atsushi
Ntt Communication Science Laboratories Ntt Corporation
-
WATANABE Shinji
NTT Communication Science Laboratories, NTT Corporation
-
UEDA Naonori
NTT Communication Science Laboratories
-
Ueda Naonori
Ntt Communication Science Laboratories Ntt Corporation
-
Watanabe Shinji
Ntt Communication Science Laboratories Ntt Corporation
関連論文
- Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection
- Efficient discriminative training of error corrective models using high-WER competitors (Speech) -- (国際ワークショップ"Asian workshop on speech science and technology")
- Efficient discriminative training of error corrective models using high-WER competitors
- Speech Recognition Based on Student's t-Distribution Derived from Total Bayesian Framework(Speech Recognition, Statistical Modeling for Speech Processing)
- Bayesian model search for mixture models based on optimizing variational bounds
- Selection of Shared-State Hidden Markov Model Structure Using Bayesian Criterion(the 2003 IEICE Excellent Paper Award)
- EM Algorithm with Split and Merge Operations for Mixture Models(Excellent Paper Originally Published in Japanese)
- Efficient Combination of Likelihood Recycling and Batch Calculation for Fast Acoustic Likelihood Calculation
- Modeling of growing networks with directional attachment and communities
- Production-Oriented Models for Speech Recognition(Speech Recognition, Statistical Modeling for Speech Processing)
- Model Shrinkage for Discriminative Language Models
- Effects of Conversational Agents on Activation of Communication in Thought-Evoking Multi-Party Dialogues