arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.13657eess.AS
收藏

基于说话人距离损失函数的语音分离增强Conv-TasNet模型

An enhanced Conv-TasNet model for speech separation using a speaker distance-based loss function

Jose A. Arango-Sánchez, Julián D. Arias-Londoño

摘要:

这项工作使用预先训练的深度学习模型解决了西班牙语中的语音分离问题。与许多语音处理任务一样,与英语不同的其他语言的大型数据库很少。因此,这项工作使用Conv-TasNet模型作为基准来探索不同的训练策略。最佳训练策略的尺度不变信号失真比(SI-SDR)度量值为9.9 dB。然后,通过实验,我们发现了说话人的相似性和模型的性能之间的反比关系,因此提出了一种改进的ConvTasNet架构。增强的Conv-TasNet模型使用预先训练的语音嵌入在代价函数中添加扬声器之间的余弦相似性项,产生10.6 dB的SI-SDR。最后,关于实时部署的最终实验显示了扬声器的通道同步中的一些缺点,这是由于需要处理仅出现一个扬声器的小语音段。

英文摘要:

This work addresses the problem of speech separation in the Spanish Language using pre-trained deep learning models. As with many speech processing tasks, large databases in other languages different from English are scarce. Therefore this work explores different training strategies using the Conv-TasNet model as a benchmark. A scale-invariant signal distortion ratio (SI-SDR) metric value of 9.9 dB was achieved for the best training strategy. Then, experimentally, we identified an inverse relationship between the speakers' similarity and the model's performance, so an improved ConvTasNet architecture was proposed. The enhanced Conv-TasNet model uses pre-trained speech embeddings to add a between-speakers cosine similarity term in the cost function, yielding an SI-SDR of 10.6 dB. Lastly, final experiments regarding real-time deployment show some drawbacks in the speakers' channel synchronization due to the need to process small speech segments where only one of the speakers appears.

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。

↑