当前位置:
X-MOL 学术
›
arXiv.cs.SD
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech
arXiv - CS - Sound Pub Date : 2020-11-24 , DOI: arxiv-2011.11818 Yiling Huang, Yutian Chen, Jason Pelecanos, Quan Wang
arXiv - CS - Sound Pub Date : 2020-11-24 , DOI: arxiv-2011.11818 Yiling Huang, Yutian Chen, Jason Pelecanos, Quan Wang
In recent years, Text-To-Speech (TTS) has been used as a data augmentation
technique for speech recognition to help complement inadequacies in the
training data. Correspondingly, we investigate the use of a multi-speaker TTS
system to synthesize speech in support of speaker recognition. In this study we
focus the analysis on tasks where a relatively small number of speakers is
available for training. We observe on our datasets that TTS synthesized speech
improves cross-domain speaker recognition performance and can be combined
effectively with multi-style training. Additionally, we explore the
effectiveness of different types of text transcripts used for TTS synthesis.
Results suggest that matching the textual content of the target domain is a
good practice, and if that is not feasible, a transcript with a sufficiently
large vocabulary is recommended.
中文翻译:
Synth2Aug:使用TTS合成语音进行跨域说话人识别
近年来,文本转语音(TTS)已被用作语音识别的数据增强技术,以帮助弥补训练数据中的不足。相应地,我们调查了使用多说话者TTS系统来合成语音以支持说话者识别的情况。在这项研究中,我们将分析重点放在任务上,这些任务需要相对较少的发言人进行培训。我们在数据集上观察到,TTS合成语音可以提高跨域说话者的识别性能,并且可以有效地与多种风格的训练相结合。此外,我们探索了用于TTS合成的不同类型的文字记录的有效性。结果表明,匹配目标域的文本内容是一种很好的做法,如果这样做不可行,
更新日期:2020-11-25
中文翻译:
Synth2Aug:使用TTS合成语音进行跨域说话人识别
近年来,文本转语音(TTS)已被用作语音识别的数据增强技术,以帮助弥补训练数据中的不足。相应地,我们调查了使用多说话者TTS系统来合成语音以支持说话者识别的情况。在这项研究中,我们将分析重点放在任务上,这些任务需要相对较少的发言人进行培训。我们在数据集上观察到,TTS合成语音可以提高跨域说话者的识别性能,并且可以有效地与多种风格的训练相结合。此外,我们探索了用于TTS合成的不同类型的文字记录的有效性。结果表明,匹配目标域的文本内容是一种很好的做法,如果这样做不可行,