Transfer the linguistic representations from TTS to accent conversion with non-parallel data
This addresses the problem of accent conversion for speech processing applications, though it appears incremental as it builds on existing TTS and conversion methods.
The paper tackles accent conversion with non-parallel data by transferring linguistic representations from TTS systems, resulting in significantly enhanced audio quality and intelligibility.
Accent conversion aims to convert the accent of a source speech to a target accent, meanwhile preserving the speaker's identity. This paper introduces a novel non-autoregressive framework for accent conversion that learns accent-agnostic linguistic representations and employs them to convert the accent in the source speech. Specifically, the proposed system aligns speech representations with linguistic representations obtained from Text-to-Speech (TTS) systems, enabling training of the accent voice conversion model on non-parallel data. Furthermore, we investigate the effectiveness of a pretraining strategy on native data and different acoustic features within our proposed framework. We conduct a comprehensive evaluation using both subjective and objective metrics to assess the performance of our approach. The evaluation results highlight the benefits of the pretraining strategy and the incorporation of richer semantic features, resulting in significantly enhanced audio quality and intelligibility.