arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01566eess.AS
收藏

重叠语音识别中的无失真多通道目标语音增强

Distortionless Multi-Channel Target Speech Enhancement for Overlapped Speech Recognition

Bo Wu, Meng Yu, Lianwu Chen, Yong Xu, Chao Weng, Dan Su, Dong Yu

摘要:

基于深度学习的语音增强技术在语音质量和可懂度方面带来了显著的改善。然而,由于增强阶段中的语音失真,由客观度量(诸如语音质量的感知评估(PESQ))测量的语音质量的大的增益不一定导致改进的语音识别性能。本文提出了一种基于频域建模的多通道扩张卷积网络,用于在远场、噪声和多说话人环境下增强目标说话人。我们研究了三种实现重叠语音识别无失真波形的方法:无限范围内估计复理想比率掩模,在多目标学习中引入fbank损失,以及通过声学模型微调增强模型。实验结果证明了这三种方法在降低语音失真和提高识别准确率方面的有效性。特别地,联合调谐增强模型与其他独立声学模型在真实测试数据上工作得非常好。

英文摘要:

Speech enhancement techniques based on deep learning have brought significant improvement on speech quality and intelligibility. Nevertheless, a large gain in speech quality measured by objective metrics, such as perceptual evaluation of speech quality (PESQ), does not necessarily lead to improved speech recognition performance due to speech distortion in the enhancement stage. In this paper, a multi-channel dilated convolutional network based frequency domain modeling is presented to enhance target speaker in the far-field, noisy and multi-talker conditions. We study three approaches towards distortionless waveforms for overlapped speech recognition: estimating complex ideal ratio mask with an infinite range, incorporating the fbank loss in a multi-objective learning and finetuning the enhancement model by an acoustic model. Experimental results proved the effectiveness of all three approaches on reducing speech distortions and improving recognition accuracy. Particularly, the jointly tuned enhancement model works very well with other standalone acoustic model on real test data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑