机译:一种用于噪声语音识别的动态参数补偿方法
School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510640, China;
Department of Electronic Engineering, City University of Hong Kong, Kowloon, Hong Kong, China;
Department of Electronic Engineering, City University of Hong Kong, Kowloon, Hong Kong, China;
School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510640, China;
Noisy speech recognition; Model compensation; Dynamic parameter combination;
机译:基于LDA派生参数和发声参数的鲁棒语音/非语音检测用于嘈杂环境中的语音识别
机译:噪声鲁棒语音识别的数据驱动模型参数补偿方法
机译:基于状态相关因子的改进的HMM参数补偿鲁棒语音识别方法
机译:基于轨迹的并行模型组合,具有统一的静态和动态参数补偿,可用于嘈杂的语音识别
机译:动态多变量化学过程中使用语音识别方法进行故障检测和诊断。
机译:级联卷积神经网络架构用于嘈杂的条件下的语音情感识别
机译:基于轨迹的并行模型组合与统一静态和动态参数补偿的带噪语音识别