Related papers: USM-VC: Mitigating Timbre Leakage with Universal S…
Disentanglement of a speaker's timbre and style is very important for style transfer in multi-speaker multi-style text-to-speech (TTS) scenarios. With the disentanglement of timbres and styles, TTS systems could synthesize expressive speech…
MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence layers across text, rhythm, and prosody, while preserving or…
Speech discrete representation has proven effective in various downstream applications due to its superior compression rate of the waveform, fast convergence during training, and compatibility with other modalities. Discrete units extracted…
Residual Vector Quantization (RVQ) has become a dominant approach in neural speech and audio coding, providing high-fidelity compression. However, speech coding presents additional challenges due to real-world noise, which degrades…
This paper introduces a novel approach to speech restoration by integrating a context-related conditioning strategy. Specifically, we employ the diffusion-based generative restoration model, UNIVERSE++, as a backbone to evaluate the…
Text-to-speech (TTS) and voice conversion (VC) are two different tasks both aiming at generating high quality speaking voice according to different input modality. Due to their similarity, this paper proposes UnifySpeech, which brings TTS…
Spurred by a huge interest in the post-Shannon communication, it has recently been shown that leveraging semantics can significantly improve the communication effectiveness across many tasks. In this article, inspired by human…
Any-to-any voice conversion aims to convert the voice from and to any speakers even unseen during training, which is much more challenging compared to one-to-one or many-to-many tasks, but much more attractive in real-world scenarios. In…
This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so as to construct a more realistic source signal. First a…
Voice conversion (VC) techniques can be abused by malicious parties to transform their audios to sound like a target speaker, making it hard for a human being or a speaker verification/identification system to trace the source speaker. In…
Automatic accent identification (AID) remains a challenging task due to the complex variability of accents, the entanglement of accent cues with speaker traits, and the scarcity of reliable accentlabelled data. To address these challenges,…
LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…
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…
The goal of this paper is to provide a new perspective on speech modeling by incorporating perceptual invariances such as amplitude scaling and temporal shifts. Conventional generative formulations often treat each dataset sample as a fixed…
This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice conversion methods focus on single-channel waveforms,…
Speech time reversal refers to the process of reversing the entire speech signal in time, causing it to play backward. Such signals are completely unintelligible since the fundamental structures of phonemes and syllables are destroyed.…
Voice conversion (VC) techniques aim to modify speaker identity of an utterance while preserving the underlying linguistic information. Most VC approaches ignore modeling of the speaking style (e.g. emotion and emphasis), which may contain…
Cross-lingual voice conversion (VC) is a task that aims to synthesize target voices with the same content while source and target speakers speak in different languages. Its challenge lies in the fact that the source and target data are…
Target speaker extraction, which aims at extracting a target speaker's voice from a mixture of voices using audio, visual or locational clues, has received much interest. Recently an audio-visual target speaker extraction has been proposed…
Generative models for speech synthesis face a fundamental trade-off: discrete tokens ensure stability but sacrifice expressivity, while continuous signals retain acoustic richness but suffer from error accumulation due to task entanglement.…