...
机译:KL-HMM的正则化说话人适应用于音调异常语音识别
Department of Bioengineering, University of Texas at Dallas, Richardson, TX, USA;
School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea;
School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea;
Department of Bioengineering, University of Texas at Dallas, Richardson, TX, USA;
School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea;
Hidden Markov models; Speech; Adaptation models; Speech recognition; Acoustics; Computational modeling; Silicon;
机译:基于HMM的语音识别和自适应合成系统的韵律演讲者的语音输入语音输出通信
机译:扬声器异常语音自动识别的困难及其对老年人使用基于语音的应用的启示:文献综述
机译:语音清晰度指数(Ψ):基于距离的语音麻痹性说话者说话者的语音质量指标和识别率预测
机译:扰动扬声器模型适应对端到端语音识别的调查
机译:用于语音和说话者识别的替代正则化神经网络架构。
机译:KL-HMM的正则化说话人适应用于音调异常语音识别
机译:用于扰动语音识别的KL-HMM的正规扬声器适应
机译:强大的语音处理和识别:说话者ID,语言ID,语音识别/关键字识别,Diarization / Co-Channel /环境表征,说话者状态评估。