Multi-Task Wavernn With An Integrated Architecture For Cross-Lingual Voice Conversion
IEEE SIGNAL PROCESSING LETTERS(2020)
摘要
Spoken languages are similar phonetically because humans have a common vocal production system. However, each language has a unique phonetic repertoire and phonotactic rule. In cross-lingual voice conversion, source speaker and target speaker speak different languages. The challenge is how to project the speaker identity of the source speaker to that of the target across two different phonetic systems. A typical voice conversion system employs a generator-vocoder pipeline, where the generator is responsible for conversion, and the vocoder is for waveform reconstruction. We propose a novel Multi-Task WaveRNN with an integrated architecture for cross-lingual voice conversion. The WaveRNN is trained on two sets of monolingual data via a two-task learning. The integrated architecture takes linguistic features as input and outputs speech waveform directly. Voice conversion experiments are conducted between English and Mandarin, which confirm the effectiveness of the proposed method in terms of speech quality and speaker similarity.
更多查看译文
关键词
Vocoders, Pipelines, Generators, Linguistics, Acoustics, Training, Task analysis, Cross-lingual voice conversion (xVC), multi-task learning (MTL), WaveRNN, integrated architecture
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络