vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders

• URL: http://arxiv.org/abs/2409.01995v2
• Date: Wed, 11 Sep 2024 04:20:50 GMT
• Title: vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders
• Authors: Yiwei Guo, Zhihan Li, Junjie Li, Chenpeng Du, Hankun Wang, Shuai Wang, Xie Chen, Kai Yu,
• Abstract summary: We propose a new speech discrete token vocoder, vec2wav 2.0, which advances voice conversion (VC) We use discrete tokens from speech self-supervised models as the content features of source speech, and treat VC as a prompted vocoding task. We show vec2wav 2.0 achieves competitive cross-lingual VC even only trained on monolingual corpus.
• Score: 26.00129172101188
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a new speech discrete token vocoder, vec2wav 2.0, which advances voice conversion (VC). We use discrete tokens from speech self-supervised models as the content features of source speech, and treat VC as a prompted vocoding task. To amend the loss of speaker timbre in the content tokens, vec2wav 2.0 utilizes the WavLM features to provide strong timbre-dependent information. A novel adaptive Snake activation function is proposed to better incorporate timbre into the waveform reconstruction process. In this way, vec2wav 2.0 learns to alter the speaker timbre appropriately given different reference prompts. Also, no supervised data is required for vec2wav 2.0 to be effectively trained. Experimental results demonstrate that vec2wav 2.0 outperforms all other baselines to a considerable margin in terms of audio quality and speaker similarity in any-to-any VC. Ablation studies verify the effects made by the proposed techniques. Moreover, vec2wav 2.0 achieves competitive cross-lingual VC even only trained on monolingual corpus. Thus, vec2wav 2.0 shows timbre can potentially be manipulated only by speech token vocoders, pushing the frontiers of VC and speech synthesis.

Related papers

• AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation [55.1650189699753]
  Direct speech-to-speech translation (S2ST) aims to convert speech from one language into another, and has demonstrated significant progress to date. Current S2ST models still suffer from distinct degradation in noisy environments and fail to translate visual speech. We present AV-TranSpeech, the first audio-visual speech-to-speech model without relying on intermediate text.
  arXiv  Detail & Related papers  (2023-05-24T17:59:03Z)
• NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers [90.83782600932567]
  We develop NaturalSpeech 2, a TTS system that leverages a neural audio predictor with residual vectorizers to get the quantized latent vectors. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, synthesis, and voice quality in a zero-shot setting.
  arXiv  Detail & Related papers  (2023-04-18T16:31:59Z)
• Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion [42.43123253495082]
  One-shot voice conversion (VC) with only a single target speaker's speech for reference has become a hot research topic. We employ random resampling for pitch and content encoder and use the variational contrastive log-ratio upper bound of mutual information to disentangle speech components. Experiments on the VCTK dataset show the model achieves state-of-the-art performance for one-shot VC in terms of naturalness and intellgibility.
  arXiv  Detail & Related papers  (2022-08-18T10:36:27Z)
• Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion [34.139871476234205]
  We investigate zero-shot voice conversion from a novel perspective of self-supervised disentangled speech representation learning. A zero-shot voice conversion is performed by feeding an arbitrary speaker embedding and content embeddings to a sequential variational autoencoder (VAE) decoder. On TIMIT and VCTK datasets, we achieve state-of-the-art performance on both objective evaluation, i.e., speaker verification (SV) on speaker embedding and content embedding, and subjective evaluation, i.e. voice naturalness and similarity, and remains to be robust even with noisy source/target utterances.
  arXiv  Detail & Related papers  (2022-03-30T23:03:19Z)
• VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion [77.50171525265056]
  This paper proposes a novel multi-speaker Video-to-Speech (VTS) system based on cross-modal knowledge transfer from voice conversion (VC) The Lip2Ind network can substitute the content encoder of VC to form a multi-speaker VTS system to convert silent video to acoustic units for reconstructing accurate spoken content.
  arXiv  Detail & Related papers  (2022-02-18T08:58:45Z)
• Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition [52.71604809100364]
  We propose wav2vec-Switch, a method to encode noise robustness into contextualized representations of speech. Specifically, we feed original-noisy speech pairs simultaneously into the wav2vec 2.0 network. In addition to the existing contrastive learning task, we switch the quantized representations of the original and noisy speech as additional prediction targets.
  arXiv  Detail & Related papers  (2021-10-11T00:08:48Z)
• Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks [14.55242023708204]
  We propose a novel Source-Filter-based Emotional VC model (SFEVC) to achieve proper filtering of speaker-independent emotion features. Our SFEVC model consists of multi-channel encoders, emotion separate encoders, and one decoder.
  arXiv  Detail & Related papers  (2021-10-04T03:14:48Z)
• VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion [54.29557210925752]
  One-shot voice conversion can be effectively achieved by speech representation disentanglement. We employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations.
  arXiv  Detail & Related papers  (2021-06-18T13:50:38Z)
• VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture [71.45920122349628]
  Auto-encoder-based VC methods disentangle the speaker and the content in input speech without given the speaker's identity. We use the U-Net architecture within an auto-encoder-based VC system to improve audio quality.
  arXiv  Detail & Related papers  (2020-06-07T14:01:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.