搜索结果: 1-7 共查到“知识库 语音处理 Speech recognition”相关记录7条 . 查询时间(0.203 秒)
STATE-DEPENDENT MIXTURE TYING WITH VARIABLE CODEBOOK SIZE FOR ACCENTED SPEECH RECOGNITION
State-dependent tied mixture models variable codebook size
2013/6/27
In this paper, we propose a state-dependent tied mixture (SDTM) models with variable codebook size to improve the model robustness for accented p honetic variations while maintaining model discrimina...
State-Dependent Phoneme-Based Model Merging for Dialectal Chinese Speech Recognition
Speech recognition dialectal Ch inese speech recognition state-dependent phoneme-based model merging acoustic modeling acoustic model distance measure
2013/6/27
Aiming at building a dialectal Chinese speech rec ognizer from a standard Chinese speech recognizer with a small am ount of dialectal Chinese speech, a novel, simple but effective acoustic modeling me...
Weighting Observation Vectors for Robust Speech Recognition in Noisy Environments
Weighting Observation Vectors Robust Speech Recognition Noisy Environments
2013/6/27
In this paper, we propose a novel approach to robust speech recognition in noisy environments by discriminating the observation vectors. In conventional HMM-based speech recognition, all the observ...
A Real-World Speech Recognition System Based on CDCPMs
Speaker-Independent Speech Recognition center-distance continuous probability model (CDCPM) embedded multiple-model (EMM)
2013/6/27
In this paper a real-world continuous-manner 2000-phrase speaker-independent Chinese speech recognition system is introduced, the vocabulary of which consists of 2000 Chinese phrases and each phrase i...
A Log-Index Weighted Cepstral Distance Measure for Speech Recognition
Log-Index Weighted Cepstral Distance Measure Speech Recognition
2013/6/27
A log-index weighted cepstral distance measure is proposed and tested in speaker-independent and speaker-dependent isolated word recognition systems using statistic techniques. The weights for the cep...
A Real-World Large Vocabulary Speaker-Independent Speech Recognition System
Real-World Large Vocabulary Speaker-Independent Speech Recognition System
2013/6/27
In this paper a real-world speaker-independent speech recognition system with2000 Chinese phrases is introduced. Several new technologies, such as knowledge leading recognition strategy, the CDCPM aco...
A New Model for Speech Recognition: Center-Distance Continuous Probability Model
A New Model Speech Recognition Center-Distance Continuous Probability Model
2013/6/27
In this paper a new statistic modelnamed Center-Distance Continuous Probability Model(CDCPM) is proposed for speech recognition, which is based on Center-Distance Normal(CDN) distribution. In a CDCPM,...