Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection
スポンサーリンク
概要
- 論文の詳細を見る
A dependency structure interprets modification relationships between words or phrases and is recognized as an important element in semantic information analysis. With the conventional approaches for extracting this dependency structure, it is assumed that the complete sentence is known before the analysis starts. For spontaneous speech data, however, this assumption is not necessarily correct since sentence boundaries are not marked in the data. Although sentence boundaries can be detected before dependency analysis, this cascaded implementation is not suitable for online processing since it delays the responses of the application. To solve these problems, we proposed a sequential dependency analysis (SDA) method for online spontaneous speech processing, which enabled us to analyze incomplete sentences sequentially and detect sentence boundaries simultaneously. In this paper, we propose an improved SDA integrating a labeling-based sentence boundary detection (SntBD) technique based on Conditional Random Fields (CRFs). In the new method, we use CRF for soft decision of sentence boundaries and combine it with SDA to retain its online framework. Since CRF-based SntBD yields better estimates of sentence boundaries, SDA can provide better results in which the dependency structure and sentence boundaries are consistent. Experimental results using spontaneous lecture speech from the Corpus of Spontaneous Japanese show that our improved SDA outperforms the original SDA with SntBD accuracy providing better dependency analysis results.
- (社)電子情報通信学会の論文
- 2010-05-01
著者
-
Nakamura Atsushi
Ntt Communication Science Laboratories Ntt Corporation
-
Oba Takanobu
Ntt Communication Science Laboratories Ntt Corporation
-
Hori Takaaki
Ntt Communication Science Laboratories Ntt Corporation
関連論文
- Improved Phoneme-History-Dependent Search Method for Large-Vocabulary Continuous-Speech Recognition
- 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)
- Selection of Shared-State Hidden Markov Model Structure Using Bayesian Criterion(the 2003 IEICE Excellent Paper Award)
- Efficient Combination of Likelihood Recycling and Batch Calculation for Fast Acoustic Likelihood Calculation
- Production-Oriented Models for Speech Recognition(Speech Recognition, Statistical Modeling for Speech Processing)
- Model Shrinkage for Discriminative Language Models