Voice Conversion with Diverse Intonation using Conditional Variational Auto-Encoder

• URL: http://arxiv.org/abs/2504.12005v1
• Date: Wed, 16 Apr 2025 11:59:56 GMT
• Title: Voice Conversion with Diverse Intonation using Conditional Variational Auto-Encoder
• Authors: Soobin Suh, Dabi Ahn, Heewoong Park, Jonghun Park,
• Abstract summary: We propose a novel approach for voice conversion with diverse intonations using conditional variational autoencoder (CVAE)<n>We have been able to convert voices with more diverse intonation by making the posterior of the latent space more complex with inverse autoregressive flow (IAF)
• Score: 1.6416145918859668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Voice conversion is a task of synthesizing an utterance with target speaker's voice while maintaining linguistic information of the source utterance. While a speaker can produce varying utterances from a single script with different intonations, conventional voice conversion models were limited to producing only one result per source input. To overcome this limitation, we propose a novel approach for voice conversion with diverse intonations using conditional variational autoencoder (CVAE). Experiments have shown that the speaker's style feature can be mapped into a latent space with Gaussian distribution. We have also been able to convert voices with more diverse intonation by making the posterior of the latent space more complex with inverse autoregressive flow (IAF). As a result, the converted voice not only has a diversity of intonations, but also has better sound quality than the model without CVAE.

Related papers

• Accent conversion using discrete units with parallel data synthesized from controllable accented TTS [56.18382038512251]
  The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used one-to-one systems that could only be trained for each non-native accent. This paper presents a promising AC model that can convert many accents into native to overcome these issues.
  arXiv  Detail & Related papers  (2024-09-30T19:52:10Z)
• Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt [50.25271407721519]
  We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language.<n>We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation.<n>Experiments show that our model achieves favorable controlling ability and audio quality.
  arXiv  Detail & Related papers  (2024-03-18T13:39:05Z)
• 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)
• Towards General-Purpose Text-Instruction-Guided Voice Conversion [84.78206348045428]
  This paper introduces a novel voice conversion model, guided by text instructions such as "articulate slowly with a deep tone" or "speak in a cheerful boyish voice" The proposed VC model is a neural language model which processes a sequence of discrete codes, resulting in the code sequence of converted speech.
  arXiv  Detail & Related papers  (2023-09-25T17:52:09Z)
• A unified one-shot prosody and speaker conversion system with self-supervised discrete speech units [94.64927912924087]
  Existing systems ignore the correlation between prosody and language content, leading to degradation of naturalness in converted speech. We devise a cascaded modular system leveraging self-supervised discrete speech units as language representation. Experiments show that our system outperforms previous approaches in naturalness, intelligibility, speaker transferability, and prosody transferability.
  arXiv  Detail & Related papers  (2022-11-12T00:54:09Z)
• Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding [6.278338686038089]
  phonetic posteriorgrams based methods have been quite popular in non-parallel singing voice conversion systems. Due to the lack of acoustic information in PPGs, style and naturalness of the converted singing voices are still limited. Our proposed model can significantly improve the naturalness of converted singing voices and the similarity with the target singer.
  arXiv  Detail & Related papers  (2021-10-10T10:27:20Z)
• StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion [19.74933410443264]
  We present an unsupervised many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Our model is trained only with 20 English speakers. It generalizes to a variety of voice conversion tasks, such as any-to-many, cross-lingual, and singing conversion.
  arXiv  Detail & Related papers  (2021-07-21T23:44:17Z)
• Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencoder [2.4975981795360847]
  We propose a new method based on feature disentanglement to tackle many to many voice conversion. The method has the capability to disentangle speaker identity and linguistic content from utterances. It can convert from many source speakers to many target speakers with a single autoencoder network.
  arXiv  Detail & Related papers  (2021-07-11T13:31:16Z)
• Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling [61.351967629600594]
  This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity.
  arXiv  Detail & Related papers  (2020-09-06T13:01:06Z)
• F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder [53.901873501494606]
  We modified and improved autoencoder-based voice conversion to disentangle content, F0, and speaker identity at the same time. We can control the F0 contour, generate speech with F0 consistent with the target speaker, and significantly improve quality and similarity.
  arXiv  Detail & Related papers  (2020-04-15T22:00:06Z)
• Vocoder-free End-to-End Voice Conversion with Transformer Network [5.5792083698526405]
  Mel-frequency filter bank (MFB) based approaches have the advantage of learning speech compared to raw spectrum since MFB has less feature size. It is possible to only use the raw spectrum along with the phase to generate different style of voices with clear pronunciation. In this paper, we introduce a vocoder-free end-to-end voice conversion method using transformer network.
  arXiv  Detail & Related papers  (2020-02-05T06:19:24Z)

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.