arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.02550eess.AScs.SD
收藏

基于注意力的多任务学习多说话人对话场景中的语音增强和说话人识别

Attention-based multi-task learning for speech-enhancement and speaker-identification in multi-speaker dialogue scenario

National Chiao Tung University(国立交通大学);Academia Sinica(中央研究院);Yuan Ze University(元智大学)

Chiang-Jen Peng, Yun-Ju Chan, Cheng Yu, Syu-Siang Wang, Yu Tsao, Tai-Shih Chi

摘要:

多任务学习(MTL)和注意机制已被证明可以有效地提取鲁棒的声学特征,用于噪声环境中的各种语音相关任务。在这项研究中,我们提出了一个基于注意力的MTL(ATM)的方法,集成MTL和注意力加权机制,同时实现多模型学习结构,执行语音增强(SE)和说话人识别(SI)。ATM系统由三部分组成:SE、SI和Attention-Net(AttNet)。SE部分由长短期记忆(LSTM)模型组成,深度神经网络(DNN)模型用于开发SI和AttNet部分。整个ATM系统首先提取代表性特征,然后在LSTM-SE中增强语音信号,并在DNN-SI中指定说话人身份。AttNet基于DNN-SI计算权重,为LSTM-SE准备更好的代表性特征。我们在噪音测试句子中测试了所提出的ATM系统对台湾普通话听力的影响。实验结果表明,该系统能够有效地提高语音质量和可懂度。此外,通过使用所提出的ATM系统,SI的准确性也可以显著提高。

英文摘要:

Multi-task learning (MTL) and attention mechanism have been proven to effectively extract robust acoustic features for various speech-related tasks in noisy environments. In this study, we propose an attention-based MTL (ATM) approach that integrates MTL and the attention-weighting mechanism to simultaneously realize a multi-model learning structure that performs speech enhancement (SE) and speaker identification (SI). The proposed ATM system consists of three parts: SE, SI, and attention-Net (AttNet). The SE part is composed of a long-short-term memory (LSTM) model, and a deep neural network (DNN) model is used to develop the SI and AttNet parts. The overall ATM system first extracts the representative features and then enhances the speech signals in LSTM-SE and specifies speaker identity in DNN-SI. The AttNet computes weights based on DNN-SI to prepare better representative features for LSTM-SE. We tested the proposed ATM system on Taiwan Mandarin hearing in noise test sentences. The evaluation results confirmed that the proposed system can effectively enhance speech quality and intelligibility of a given noisy input. Moreover, the accuracy of the SI can also be notably improved by using the proposed ATM system.

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。

↑