位置：成果数据库 > 会议 > 会议详情页
Accelerating segment model decoding for lvcsr by parallel processing of neighboring segments
  • 所属机构名称：中国科学院自动化研究所
  • 会议名称：6th International Symposium on Neural Networks, ISNN 2009
  • 成果类型：会议
  • 会场：Wuhan, China
  • 相关项目：基于语音知识和全局最优准则指导的段模型汉语LVCSR方法研究
作者： Zhang, Hua|Liu, Wen-Ju|Peng, Shouye|
同会议论文项目
基于语音知识和全局最优准则指导的段模型汉语LVCSR方法研究
期刊论文 21 会议论文 25 获奖 2 专利 3
同项目会议论文
An improved a priori MMSE spectral subtraction method for speech
Combining machine learning and computational auditory scene analysis to separate monaural speech of
Context Constrained-Generalized Posterior Probability for Verifying Phone Transcriptions
Harmonics template and application in computational auditory scene analysis for co-channel speech
An effective approach for speech enhancement by multi-band MMSE spectral subtraction
Pitch prediction from MFCC vectors using support vector regression
Microphone array speech enhancement based on a generalized post-filter and a novel perceptual filter
A two-stage algorithm for multi-speaker identification system
HMM-based phonemic distance in different speaking styles and its influence on substitutions in manda
Monaural voiced speech segregation based on elaborate harmonic grouping strategy
Durational characteristics and pitch characteristics of the prosodic phrase in Mandarin Chinese
AUTOMATIC PROSODY BOUNDARY LABELING OF MANDARIN USING BOTH TEXT AND ACOUSTIC INFORMATION
Microphone array post-filter based on auditory filtering
基于加权相关谱和的多基音检测
Stochastic segment model decoding algorithm based on neighboring segments and its application in LVC
Fast and robust stochastic segment model for mandarin digital string recognition
A novel interpolated n-gram language model based on class hierarchy
An improved a priori MMSE spectral subtraction method for speech enhancement
Research on adaptive step decoding in segment-based LVCSR
An improvement of HSMM-based speech synthesis by duration-dependent state transition probabilities
Research on segment acoustic model based mandarin LVCSR
A new language model adaptation framework using modification of structures of background corpus and
Improved syllable based acoustic modeling by inter-syllable transition model for continuous chinese
Improved large vocabulary Mandarin speech recognition using prosodic and lexical information in maxi