Related papers: Speech Synthesis From Continuous Features Using Pe…

While FastSpeech2 aims to integrate aspects of speech such as pitch, energy, and duration as conditional inputs, it still leaves scope for richer representations. As a part of this work, we leverage representations from various…

Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from…

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers,…

Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide…

Neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the synthetic speech often represents the average prosodic style of the database instead of having more versatile prosodic…

The goal of this work is zero-shot text-to-speech synthesis, with speaking styles and voices learnt from facial characteristics. Inspired by the natural fact that people can imagine the voice of someone when they look at his or her face, we…

Most existing text-to-speech (TTS) systems either synthesize speech sentence by sentence and stitch the results together, or drive synthesis from plain-text dialogues alone. Both approaches leave models with little understanding of global…

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…

While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation that unifies Foreign…

Modern zero-shot text-to-speech (TTS) models offer unprecedented expressivity but also pose serious crime risks, as they can synthesize voices of individuals who never consented. In this context, speaker unlearning aims to prevent the…

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires…

While recent zero-shot multi-speaker text-to-speech (TTS) models achieve impressive results, they typically rely on extensive transcribed speech datasets from numerous speakers and intricate training pipelines. Meanwhile, self-supervised…

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications. To address…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection…

Talking head synthesis is a promising approach for the video production industry. Recently, a lot of effort has been devoted in this research area to improve the generation quality or enhance the model generalization. However, there are few…

Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a…

The exponential surge in high-resolution remote sensing data faces a severe bottleneck in satellite-to-ground transmission. Limited downlink bandwidth forces the use of extreme high-ratio compression, which irreversibly destroys…

In debating, rebuttal is one of the most critical stages, where a speaker addresses the arguments presented by the opposing side. During this process, the speaker synthesizes their own persuasive articulation given the context from the…