Discriminative Approach to Build Hybrid Vocabulary for Conversational Telephone Speech Recognition of Agglutinative Languages
スポンサーリンク
概要
- 論文の詳細を見る
Morphemes, which are obtained from morphological parsing, and statistical sub-words, which are derived from data-driven splitting, are commonly used as the recognition units for speech recognition of agglutinative languages. In this letter, we propose a discriminative approach to select the splitting result, which is more likely to improve the recognizer's performance, for each distinct word type. An objective function which involves the unigram language model (LM) probability and the count of misrecognized phones on the acoustic training data is defined and minimized. After determining the splitting result for each word in the text corpus, we select the frequent units to build a hybrid vocabulary including morphemes and statistical sub-words. Compared to a statistical sub-word based system, the hybrid system achieves 0.8% letter error rates (LERs) reduction on the test set.
- The Institute of Electronics, Information and Communication Engineersの論文
著者
-
Yan Yonghong
Key Laboratory Of Speech Acoustics And Content Understanding Chinese Academy Of Sciences
-
Li Xin
Key Laboratory Of Automobile Materials Department Of Materials Science And Engineering Jilin University
-
ZHAO Qingwei
Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences
-
PAN Jielin
Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences
-
YAN Yonghong
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences
-
YAN Yonghong
Key Laboratory of Speech Acoustics and Content Understanding
-
LI Xin
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences
-
ZHAO Qingwei
Key Laboratory of Speech Acoustics and Content Understanding
関連論文
- Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification
- Logarithmic Adaptive Quantization Projection for Audio Watermarking
- Noise Robust Feature Scheme for Automatic Speech Recognition Based on Auditory Perceptual Mechanisms
- A Forced Alignment Based Approach for English Passage Reading Assessment
- Influence of Welding Speed on Microstructures and Properties of Ultra-high Strength Steel Sheets in Laser Welding
- A Novel Discriminative Method for Pronunciation Quality Assessment
- Discriminative Approach to Build Hybrid Vocabulary for Conversational Telephone Speech Recognition of Agglutinative Languages
- Logarithmic Adaptive Quantization Projection for Audio Watermarking
- Smoothing Method for Improved Minimum Phone Error Linear Regression