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 2406.02250eess.AScs.SD
收藏

具有灵活采样率控制的多阶段语音带宽扩展

Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control

National Engineering Research Center of Speech and Language Information Processing(国家语言与语音信息处理工程研究中心);University of Science and Technology of China(中国科学技术大学)

Ye-Xin Lu, Yang Ai, Zheng-Yan Sheng, Zhen-Hua Ling

AI总结:

提出多阶段语音带宽扩展模型MS-BWE,通过级联双流架构实现幅度与相位的逐阶段扩展及灵活采样率控制,质量媲美SOTA且生成效率极高。

摘要:

现有的大多数语音带宽扩展(BWE)方法在固定的源采样率和目标采样率约束下运行,这限制了它们在实际应用中的灵活性。在本文中,我们提出了一种名为MS-BWE的多阶段语音BWE模型,该模型可以处理一组源和目标采样率对,并实现频带宽度的灵活扩展。所提出的MS-BWE模型由一系列级联的BWE块组成,每个块采用双流架构来实现幅度和相位扩展,逐阶段逐步绘制语音频带。采用teacher-forcing策略以缓解训练与推理之间的差异。实验结果表明,我们提出的MS-BWE在语音质量上可与最先进的语音BWE方法相媲美。在生成效率方面,MS-BWE的单阶段生成在GPU上可实现超过一千倍的实时,在CPU上约为六十倍的实时。

英文摘要:

The majority of existing speech bandwidth extension (BWE) methods operate under the constraint of fixed source and target sampling rates, which limits their flexibility in practical applications. In this paper, we propose a multi-stage speech BWE model named MS-BWE, which can handle a set of source and target sampling rate pairs and achieve flexible extensions of frequency bandwidth. The proposed MS-BWE model comprises a cascade of BWE blocks, with each block featuring a dual-stream architecture to realize amplitude and phase extension, progressively painting the speech frequency bands stage by stage. The teacher-forcing strategy is employed to mitigate the discrepancy between training and inference. Experimental results demonstrate that our proposed MS-BWE is comparable to state-of-the-art speech BWE methods in speech quality. Regarding generation efficiency, the one-stage generation of MS-BWE can achieve over one thousand times real-time on GPU and about sixty times on CPU.

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。

↑