Transfer the linguistic representations from TTS to accent conversion with non-parallel data
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
Overview of the Amphion Toolkit (v0.2)
SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction
An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR
ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
토론
이 논문과 연결된 포럼 글이 아직 없습니다.