Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features

• URL: http://arxiv.org/abs/2112.04424v1
• Date: Wed, 8 Dec 2021 17:27:39 GMT
• Title: Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features
• Authors: Trung Dang, Dung Tran, Peter Chin, Kazuhito Koishida
• Abstract summary: Unsampling Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker. We show that high-quality audio samples can be achieved by using a length resupervised decoder.
• Score: 24.182732872327183
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation has been shown to produce useful linguistic units without using transcripts, which can be directly passed to a VC model. In this paper, we showed that high-quality audio samples can be achieved by using a length resampling decoder, which enables the VC model to work in conjunction with different linguistic feature extractors and vocoders without requiring them to operate on the same sequence length. We showed that our method can outperform many baselines on the VCTK dataset. Without modifying the architecture, we further demonstrated that a) using pairs of different audio segments from the same speaker, b) adding a cycle consistency loss, and c) adding a speaker classification loss can help to learn a better speaker embedding. Our model trained on LibriTTS using these techniques achieves the best performance, producing audio samples transferred well to the target speaker's voice, while preserving the linguistic content that is comparable with actual human utterances in terms of Character Error Rate.

Related papers

• Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations [14.437646262239612]
  Self-supervised Voice Conversion (VC) architecture can be used to learn to encode transitory features, such as content, separately from stationary ones, such as speaker ID or recording conditions, creating speaker-disentangled representations. Using speaker-disentangled codes to train LLMs for text-to-speech (TTS) allows the LLM to generate the content and the style of the speech only from the text, similarly to humans, while the speaker identity is provided by the decoder of the VC model. Results show that LLMs trained over speaker-disentangled self-supervised representations provide an improvement of 4.7pp
  arXiv  Detail & Related papers  (2024-02-05T15:08:19Z)
• SelfVC: Voice Conversion With Iterative Refinement using Self Transformations [42.97689861071184]
  SelfVC is a training strategy to improve a voice conversion model with self-synthesized examples. We develop techniques to derive prosodic information from the audio signal and SSL representations to train predictive submodules in the synthesis model. Our framework is trained without any text and achieves state-of-the-art results in zero-shot voice conversion on metrics evaluating naturalness, speaker similarity, and intelligibility of synthesized audio.
  arXiv  Detail & Related papers  (2023-10-14T19:51:17Z)
• Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer [53.72998363956454]
  Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy. The scarcity of high-quality speaker-parallel data poses a challenge for learning style transfer during translation. We design an S2ST pipeline with style-transfer capability on the basis of discrete self-supervised speech representations and timbre units.
  arXiv  Detail & Related papers  (2023-09-14T09:52:08Z)
• Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model [13.572330725278066]
  A novel point of the proposed method is the direct use of the SSL model to obtain embedding vectors from speech representations trained with a large amount of data. The disentangled embeddings will enable us to achieve better reproduction performance for unseen speakers and rhythm transfer conditioned by different speeches.
  arXiv  Detail & Related papers  (2023-04-24T10:15:58Z)
• Continual Learning for On-Device Speech Recognition using Disentangled Conformers [54.32320258055716]
  We introduce a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks. We propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform baselines on general ASR.
  arXiv  Detail & Related papers  (2022-12-02T18:58:51Z)
• 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)
• 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)
• Many-to-Many Voice Transformer Network [55.17770019619078]
  This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework. It enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech.
  arXiv  Detail & Related papers  (2020-05-18T04:02:08Z)
• Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation [125.59372403631006]
  We propose a semi-supervised learning approach for multi-speaker text-to-speech (TTS) A multi-speaker TTS model can learn from the untranscribed audio via the proposed encoder-decoder framework with discrete speech representation. We found the model can benefit from the proposed semi-supervised learning approach even when part of the unpaired speech data is noisy.
  arXiv  Detail & Related papers  (2020-05-16T15:47:11Z)
• Unsupervised Audiovisual Synthesis via Exemplar Autoencoders [59.13989658692953]
  We present an unsupervised approach that converts the input speech of any individual into audiovisual streams of potentially-infinitely many output speakers. We use Exemplar Autoencoders to learn the voice, stylistic prosody, and visual appearance of a specific target speech exemplar.
  arXiv  Detail & Related papers  (2020-01-13T18:56:45Z)

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.