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 2308.03332cs.SDcs.AIeess.AS
收藏

利用BGRU与GMM改进深度吸引子网络以实现语音分离

Improving Deep Attractor Network by BGRU and GMM for Speech Separation

Rawad Melhem, Assef Jafar, Riad Hamadeh

AI总结:

本文提出用BGRU替代BLSTM、用GMM替代k-means来简化并增强深度吸引子网络,在TIMIT两说话人混合语音分离任务上取得更高SDR和PESQ,同时减少参数和训练时间,并在阿拉伯语混合语音上表现更优。

摘要:

深度吸引子网络(DANet)是语音分离领域最先进的技术,它使用双向长短期记忆网络(BLSTM),但DANet模型的复杂度非常高。本文提出了一种简化且性能更强的DANet模型,使用双向门控神经网络(BGRU)替代BLSTM。在DANet中采用高斯混合模型(GMM)而非k-means作为聚类算法,以降低复杂度并提高学习速度和准确率。本文使用的评价指标包括信号失真比(SDR)、信号干扰比(SIR)、信号伪影比(SAR)和语音质量感知评估(PESQ)分数。从TIMIT语料库中准备了两说话人混合数据集来评估所提出的模型,系统在SDR和PESQ分数上分别达到了12.3 dB和2.94,优于原始DANet模型。其他改进包括参数数量减少了20.7%,训练时间减少了17.9%。该模型还被应用于混合阿拉伯语语音信号,结果优于英语语音。

英文摘要:

Deep Attractor Network (DANet) is the state-of-the-art technique in speech separation field, which uses Bidirectional Long Short-Term Memory (BLSTM), but the complexity of the DANet model is very high. In this paper, a simplified and powerful DANet model is proposed using Bidirectional Gated neural network (BGRU) instead of BLSTM. The Gaussian Mixture Model (GMM) other than the k-means was applied in DANet as a clustering algorithm to reduce the complexity and increase the learning speed and accuracy. The metrics used in this paper are Signal to Distortion Ratio (SDR), Signal to Interference Ratio (SIR), Signal to Artifact Ratio (SAR), and Perceptual Evaluation Speech Quality (PESQ) score. Two speaker mixture datasets from TIMIT corpus were prepared to evaluate the proposed model, and the system achieved 12.3 dB and 2.94 for SDR and PESQ scores respectively, which were better than the original DANet model. Other improvements were 20.7% and 17.9% in the number of parameters and time training, respectively. The model was applied on mixed Arabic speech signals and the results were better than that in English.

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。

↑