A novel speakeradaptation method named maximum likelihood model interpolation (MLMI) is proposed.
本文提出了一种新的说话人自适应算法———最大似然模型插值。
2
Speakeradaptation is one of the effective approaches to improve the performance of speaker-independent speech recognition.
说话人自适应是提高非特定人语音识别性能的有效方法之一。
3
A novel model-based speakeradaptation algorithm, support speaker weighting(SSW), was proposed for rapid speakeradaptation in speech recognition systems.