Related papers: Diffusion-Based Voice Conversion with Fast Maximum…
A diffusion-based voice conversion (VC) model (e.g., VoiceGrad) can achieve high speech quality and speaker similarity; however, its conversion process is slow owing to iterative sampling. FastVoiceGrad overcomes this limitation by…
This paper introduces a novel data-driven strategy for synthesizing gramophone noise audio textures. A diffusion probabilistic model is applied to generate highly realistic quasiperiodic noises. The proposed model is designed to generate…
This paper is about developing personalized speech synthesis systems with recordings of mildly impaired speech. In particular, we consider consonant and vowel alterations resulted from partial glossectomy, the surgical removal of part of…
Zero-shot voice conversion aims to transform a source speech utterance to match the timbre of a reference speech from an unseen speaker. Traditional approaches struggle with timbre leakage, insufficient timbre representation, and mismatches…
Expressive voice conversion (VC) conducts speaker identity conversion for emotional speakers by jointly converting speaker identity and emotional style. Emotional style modeling for arbitrary speakers in expressive VC has not been…
Speech emotion conversion is the task of converting the expressed emotion of a spoken utterance to a target emotion while preserving the lexical content and speaker identity. While most existing works in speech emotion conversion rely on…
Although voice conversion (VC) systems have shown a remarkable ability to transfer voice style, existing methods still have an inaccurate pitch and low speaker adaptation quality. To address these challenges, we introduce Diff-HierVC, a…
Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive…
Speech-to-speech translation (S2ST) aims to convert spoken input in one language to spoken output in another, typically focusing on either language translation or accent adaptation. However, effective cross-cultural communication requires…
Human speech exhibits rich and flexible prosodic variations. To address the one-to-many mapping problem from text to prosody in a reasonable and flexible manner, we propose DiffStyleTTS, a multi-speaker acoustic model based on a conditional…
Voice conversion as the style transfer task applied to speech, refers to converting one person's speech into a new speech that sounds like another person's. Up to now, there has been a lot of research devoted to better implementation of VC…
While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…
Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating…
We study the problem of cross-lingual voice conversion in non-parallel speech corpora and one-shot learning setting. Most prior work require either parallel speech corpora or enough amount of training data from a target speaker. However, we…
Zero-shot voice conversion aims to transfer the voice of a source speaker to that of a speaker unseen during training, while preserving the content information. Although various methods have been proposed to reconstruct speaker information…
One-shot voice conversion (VC) with only a single target speaker's speech for reference has become a hot research topic. Existing works generally disentangle timbre, while information about pitch, rhythm and content is still mixed together.…
In recent years, diffusion-based generative models have demonstrated remarkable performance in speech conversion, including Denoising Diffusion Probabilistic Models (DDPM) and others. However, the advantages of these models come at the cost…
Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a…
Recent progress in deep generative models has improved the quality of neural vocoders in speech domain. However, generating a high-quality singing voice remains challenging due to a wider variety of musical expressions in pitch, loudness,…
In this work, we build upon our previous publication and use diffusion-based generative models for speech enhancement. We present a detailed overview of the diffusion process that is based on a stochastic differential equation and delve…