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 2211.06646eess.AScs.AIcs.LGcs.SD
收藏

基于自监督分帧嵌入的高效语音质量评估

Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings

Logitech(罗技)

Karl El Hajal, Zihan Wu, Neil Scheidwasser-Clow, Gasser Elbanna, Milos Cernak

摘要:

自动语音质量评估对于音频研究人员、开发人员、语音和语言病理学家以及系统质量工程师来说至关重要。目前最先进的系统是基于帧的语音功能(手工设计或学习)结合时间依赖性建模。本文提出了一种高效的系统,其结果可与ConferencingSpeech 2022挑战中的最佳性能模型相媲美。我们提出的系统的特点是参数数量较少(40- 60倍),FLOPS更少(100倍),内存消耗更低(10- 15倍),延迟更低(30倍)。因此,语音质量从业者可以更快地部署系统,在资源有限的硬件上部署系统,总体而言,所提出的系统有助于可持续的机器学习。本文还得出结论,逐帧嵌入优于话语级嵌入,并且具有声学条件建模的多任务训练不会降低语音质量预测,同时提供更好的解释。

英文摘要:

Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered or learnable) combined with time dependency modeling. This paper proposes an efficient system with results comparable to the best performing model in the ConferencingSpeech 2022 challenge. Our proposed system is characterized by a smaller number of parameters (40-60x), fewer FLOPS (100x), lower memory consumption (10-15x), and lower latency (30x). Speech quality practitioners can therefore iterate much faster, deploy the system on resource-limited hardware, and, overall, the proposed system contributes to sustainable machine learning. The paper also concludes that framewise embeddings outperform utterance-level embeddings and that multi-task training with acoustic conditions modeling does not degrade speech quality prediction while providing better interpretation.

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。

↑