arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2008.03687eess.AScs.CLcs.LG
收藏

LRSeep:极低资源的语音合成与识别

LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition

Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);Zhejiang University(浙江大学);Microsoft Research Asia(微软亚洲研究院);Microsoft Azure Speech(微软 Azure 语音)

Jin Xu, Xu Tan, Yi Ren, Tao Qin, Jian Li, Sheng Zhao, Tie-Yan Liu

摘要:

语音合成(text to speech,TTS)和识别(自动语音识别,ASR)是重要的语音任务,并且需要大量的文本和语音对用于模型训练。然而,世界上有超过6,000种语言,大多数语言都缺乏语音训练数据,这在为资源极低的语言构建TTS和ASR系统时带来了巨大的挑战。在本文中,我们开发了LRSpeech,一个在极低资源环境下的TTS和ASR系统,它可以支持稀有语言,低数据成本。LRSeep包括三个关键技术:1)对资源丰富的语言进行预训练,并对资源不足的语言进行微调; 2)TTS和ASR之间的双重转换,以迭代方式提高彼此的准确性; 3)知识蒸馏,以定制高质量目标说话人语音的TTS模型,并改进多个语音的ASR模型。我们进行实验的实验语言(英语)和一个真正的低资源的语言(立陶宛语),以验证LRSeech的有效性。实验结果表明,LRSeep 1)在合成语音的可懂度(超过98%的可懂度)和自然度(超过3.5的平均意见得分(MOS))方面实现了高质量的TTS,满足工业部署的要求,2)实现了有希望的ASR识别准确率,3)最后但并非最不重要的是,使用极低资源的训练数据。我们还利用不同数量的数据资源对LRSeech进行全面分析,为行业部署提供有价值的见解和指导。我们目前正在将LRSpeech部署到商业化的云语音服务中,以支持更多稀有语言的TTS。

英文摘要:

Speech synthesis (text to speech, TTS) and recognition (automatic speech recognition, ASR) are important speech tasks, and require a large amount of text and speech pairs for model training. However, there are more than 6,000 languages in the world and most languages are lack of speech training data, which poses significant challenges when building TTS and ASR systems for extremely low-resource languages. In this paper, we develop LRSpeech, a TTS and ASR system under the extremely low-resource setting, which can support rare languages with low data cost. LRSpeech consists of three key techniques: 1) pre-training on rich-resource languages and fine-tuning on low-resource languages; 2) dual transformation between TTS and ASR to iteratively boost the accuracy of each other; 3) knowledge distillation to customize the TTS model on a high-quality target-speaker voice and improve the ASR model on multiple voices. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. Experimental results show that LRSpeech 1) achieves high quality for TTS in terms of both intelligibility (more than 98% intelligibility rate) and naturalness (above 3.5 mean opinion score (MOS)) of the synthesized speech, which satisfy the requirements for industrial deployment, 2) achieves promising recognition accuracy for ASR, and 3) last but not least, uses extremely low-resource training data. We also conduct comprehensive analyses on LRSpeech with different amounts of data resources, and provide valuable insights and guidances for industrial deployment. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.

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。

↑