相关论文: Pheme: Efficient and Conversational Speech Generat…

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…

Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized…

This paper explores multi-modal controllable Text-to-Speech Synthesis (TTS) where the voice can be generated from face image, and the characteristics of output speech (e.g., pace, noise level, distance, tone, place) can be controllable with…

We consider the generative modeling of speech over multiple minutes, a requirement for long-form multimedia generation and audio-native voice assistants. However, textless spoken language models struggle to generate plausible speech past…

Controllable speech generation methods typically rely on single or fixed prompts, hindering creativity and flexibility. These limitations make it difficult to meet specific user needs in certain scenarios, such as adjusting the style while…

Recent advances in large language models (LLMs) and development of audio codecs greatly propel the zero-shot TTS. They can synthesize personalized speech with only a 3-second speech of an unseen speaker as acoustic prompt. However, they…

Target speaker extraction (TSE) aims to isolate a desired speaker's voice from a multi-speaker mixture using auxiliary information such as a reference utterance. Although recent advances in diffusion and flow-matching models have improved…

In target speaker extraction (TSE), we aim to recover target speech from a multi-talker mixture using a short enrollment utterance as reference. Recent studies on diffusion and flow-matching generators have improved target-speech fidelity.…

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Virtual humans have gained considerable attention in numerous industries, e.g., entertainment and e-commerce. As a core technology, synthesizing photorealistic face frames from target speech and facial identity has been actively studied…

Reference-based Text-to-Speech (TTS) models can generate multiple, prosodically-different renditions of the same target text. Such models jointly learn a latent acoustic space during training, which can be sampled from during inference.…

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent…

Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented…

Traditional text-to-speech (TTS) methods primarily focus on establishing a mapping between phonemes and mel-spectrograms. However, during the phoneme encoding stage, there is often a lack of real mel-spectrogram auxiliary information, which…

Speech synthesis has significantly advanced from statistical methods to deep neural network architectures, leading to various text-to-speech (TTS) models that closely mimic human speech patterns. However, capturing nuances such as emotion…

Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear…

Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large…

Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vision-driven Text-to-speech (TTS) scholars grounded their…

Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by limited training data or information loss during knowledge…

We introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of…