arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.07090eess.AS
收藏

使用领域特定的语音克隆语音增强口语语料库

Spoken Language Corpora Augmentation with Domain-Specific Voice-Cloned Speech

Mateusz Czyżnikiewicz, Łukasz Bondaruk, Jakub Kubiak, Adam Wiącek, Łukasz Degórski, Marek Kubis, Paweł Skórzewski

AI总结:

本文研究领域特定合成样本增强口语语料库对语音识别系统的影响,对比传统神经TTS与零样本语音克隆生成的不同语音数量合成数据,发现高多语音性的语音克隆数据更有效,且高可变性数据能持续提升ASR质量。

摘要:

本文研究了使用领域特定的合成样本增强口语语料库对训练语音识别系统的影响。我们使用传统的神经TTS系统和具有语音克隆能力的零样本系统,生成了不同语音数量的语音语料库。我们将添加通过这两种方法生成的不同数量合成数据训练的语音识别模型,与仅使用语音录制训练的基线模型进行比较。我们发现,虽然语音克隆数据集的质量较低,但其更高的多语音性使其比使用传统神经TTS系统合成的仅少数语音的数据集更有效。此外,我们的实验表明,使用低可变性的合成语音会迅速导致ASR质量饱和,而高可变性语音即使在将训练数据总量增加30%时仍能提供改进。

英文摘要:

In this paper we study the impact of augmenting spoken language corpora with domain-specific synthetic samples for the purpose of training a speech recognition system. Using both a conventional neural TTS system and a zero-shot one with voice cloning ability we generate speech corpora that vary in the number of voices. We compare speech recognition models trained with addition of different amounts of synthetic data generated using these two methods with a baseline model trained solely on voice recordings. We show that while the quality of voice-cloned dataset is lower, its increased multivoiceity makes it much more effective than the one with only a few voices synthesized with the use of a conventional neural TTS system. Furthermore, our experiments indicate that using low variability synthetic speech quickly leads to saturation in the quality of the ASR whereas high variability speech provides improvement even when increasing total amount of data used for training by 30%.

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。

↑