Related papers: StarGAN-VC2: Rethinking Conditional Methods for St…
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.…
This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output…
Many existing works on voice conversion (VC) tasks use automatic speech recognition (ASR) models for ensuring linguistic consistency between source and converted samples. However, for the low-data resource domains, training a high-quality…
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this…
Zero-shot voice conversion (VC) converts source speech into the voice of any desired speaker using only one utterance of the speaker without requiring additional model updates. Typical methods use a speaker representation from a pre-trained…
Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…
Voice conversion aims to modify the source speaker's voice to resemble the target speaker while preserving the original speech content. Despite notable advancements in voice conversion these days, multi-lingual voice conversion (including…
This paper introduces Taco-VC, a novel architecture for voice conversion based on Tacotron synthesizer, which is a sequence-to-sequence with attention model. The training of multi-speaker voice conversion systems requires a large number of…
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…
Foreign accent conversion (FAC) is a special application of voice conversion (VC) which aims to convert the accented speech of a non-native speaker to a native-sounding speech with the same speaker identity. FAC is difficult since the…
We introduce LinearVC, a simple voice conversion method that sheds light on the structure of self-supervised representations. First, we show that simple linear transformations of self-supervised features effectively convert voices. Next, we…
In a recent acoustic scene classification (ASC) research field, training and test device channel mismatch have become an issue for the real world implementation. To address the issue, this paper proposes a channel domain conversion using…
We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a…
Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or…
Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. However, most, if not all, existing speech enhancement GANs (SEGAN) make use of a single generator to perform one-stage enhancement…
Training a model to perform a task typically requires a large amount of data from the domains in which the task will be applied. However, it is often the case that data are abundant in some domains but scarce in others. Domain adaptation…
Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…
Emotional voice conversion (VC) aims to convert a neutral voice to an emotional (e.g. happy) one while retaining the linguistic information and speaker identity. We note that the decoupling of emotional features from other speech…
We present S$^2$Voice, the winning system of the Singing Voice Conversion Challenge (SVCC) 2025 for both the in-domain and zero-shot singing style conversion tracks. Built on the strong two-stage Vevo baseline, S$^2$Voice advances style…
Have you ever wondered how a song might sound if performed by a different artist? In this work, we propose SCM-GAN, an end-to-end non-parallel song conversion system powered by generative adversarial and transfer learning that allows users…