...语料 并没有显著的影响,而由RealAudio 的压缩结果更可进一步说明实验室原先收集 的广播语音属相当程度的干净语音(Clean Speech),经过这样破坏性的压缩过程 也没有对原本的语音信号产生太大的影响。
基于18个网页-相关网页
pseudo clean speech model 伪干净语音模型
The conventional sub-band methods can improve the recognition accuracy of noisy speech, but degrade that of clean speech.
传统的子带特征方法虽然能提高噪声下的语音识别性能,但通常会使无噪声情况下的识别性能下降。
Speech enhancement tries to extract clean speech signal from original one with noise and improve the SNR of speech signal.
语音增强则从含噪信号中提取干净的语音信号,提高语音信号的信噪比。
MLLR adaptations are conducted to evaluate the performances of the HMM recognizers, which are trained from the clean speech and generated data respectively.
识别试验利用模拟电话语音评估了HMM识别器做MLLR自适应前后的性能。
应用推荐