搜索结果: 1-10 共查到“理论语言学 continuous speech recognition”相关记录10条 . 查询时间(0.068 秒)
Two-Stage Continuous Speech Recognition Using Feature-Based Models: A Preliminary Study
Feature-Based Models Preliminary Study
2015/3/11
Two-Stage Continuous Speech Recognition Using Feature-Based Models: A Preliminary Study.
Minimum classification error training of landmark models for real-time continuous speech recognition
landmark models real-time continuous speech recognition
2015/3/11
Minimum classification error training of landmark models for real-time continuous speech recognition.
PocketSUMMIT: Small-Footprint Continuous Speech Recognition
speech recognition small footprint
2015/3/10
PocketSUMMIT: Small-Footprint Continuous Speech Recognition.
Discriminative Training of Hierarchical Acoustic Models for Large Vocabulary Continuous Speech Recognition
Hierarchical Acoustic Models Large Vocabulary Continuous Speech Recognition
2015/3/10
Discriminative Training of Hierarchical Acoustic Models for Large Vocabulary Continuous Speech Recognition.
SEMI-CONTINUOUS SEGMENTAL PROBABILITY MODELING FOR CONTINUOUS SPEECH RECOGNITION
semi-continuous segmental probability model (SCSPM) speech recognition unit mixed Gaussian densities pruning technique
2013/6/27
In this paper the design of semi-continuous segmental probability models (SCSPMs) in large vocabulary continuous speech recogn ition is presented. The tied Gaussian densities are trained using data fr...
ACOUSTIC LEVEL ERROR ANALYSIS IN CONTINUOUS SPEECH RECOGNITION
continuous speech recognition judge rules error analysis
2013/6/27
In this paper, we make a detailed analysis on the errors that may occur in a continuous speech recognition system, and define two sets of judge rules to perform the error analysis. Using these judge r...
THE HIDDEN MARKOV MODEL OF CO-ARTICULATION AND ITS APPLICATION TO THE CONTINUOUS SPEECH RECOGNITION
Speech recognition High-order HMM Hybrid HMM/MLP
2013/6/27
the co-articulation is one of the main reasons that makes the speech recogn ition difficult. However, the traditional Hidden Markov Models(HMM) can not model the co-articulation, because they depend ...
STATISTICAL KNOWLEDGE BASED FRAME SYNCHRONOUS SEARCH STRATEGIES IN CONTINUOUS SPEECH RECOGNITION
STATISTICAL KNOWLEDGE BASED FRAME SYNCHRONOUS SEARCH STRATEGIES CONTINUOUS SPEECH RECOGNITION
2013/6/27
In this paper, we propose a novel and efficient search algorithm for the Continuous Speech Recognition (CSR). The proposed algorithm is on the basis of the traditional Frame Synchronous Search (FSS) a...
RESEARCH ON CHINESE CONTINUOUS SPEECH RECOGNITION SYSTEM AND KNOWLEDGE BASED SEARCH STRATEGIES
continuous speech recognition statistical knowledge based frame synchronous search differential state dwell distribution
2013/6/27
In this paper, the principle of a Chinese continuous speech recognition system is introduced, the modeling and search strategies of its acoustic layer and language layer are also discussed in detail. ...
Research on automatic syllable detection in Chinese continuous speech recognition
Research automatic syllable detection Chinese continuous speech recognition
2013/6/27
In this paper a new sort of technology for syllable-detection in Continuous Chinese Speech Recognition is proposed, which uses smoothed frame energy curve as its main criterion and the relative thre...