位置：成果数据库 > 会议 > 会议详情页
Probabilistic latent?speaker training for large vocabulary speech recognition
  • 所属机构名称：北京大学
  • 成果类型：会议
  • 相关项目：语音识别中多层语言知识建模及全局解码算法研究
同会议论文项目
语音识别中多层语言知识建模及全局解码算法研究
期刊论文 3 会议论文 16
同项目会议论文
Integrating Multi-level Linguistic Knowledge with a Unified Framework for Mandarin Speech Recognitio
Binaural sound source localization based on steered beamformer with spherical scatterer
Refine Bigram PLSA Model by Assigning Latent Topics Unevenly
Context Dependent Syllable Acoustic Model for Continuous Chinese Speech Recognition
Speaker Identification by Local Factor Analysis and Classifier Combination
PKU Mandarin Speech Synthesis System for Blizzard 2009
Exploiting prosodic and lexical feature for tone modeling in a conditional random field framework.
中文自然语言处理技术
PHMM based asynchronous acoustic model for Chinese large vocabulary continuous speech recognition
Gmm-hmm acoustic model training by a two level procedure with Gaussian components determined by auto
Maximum entropy based tone modeling for Mandarin speech recognition
Refining Grammars for Parsing with Hierarchical Semantic Knowledge
Text Segmentation with LDA-Based Fisher Kernel
Monaural speech separation based on multi-scale fan-chirp transform
Probabilistic Latent Speaker Analysis for Large Vocabulary Speech Recognition