Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is
important to capture the diversity in human speech such as speaker identities, prosodies …

In recent years, foundation models (FMs) such as large language models (LLMs) and latent
diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This …

We introduce Matcha-TTS, a new encoder-decoder architecture for speedy TTS acoustic
modelling, trained using optimal-transport conditional flow matching (OT-CFM). This yields …

Large language models (LLM)-based speech synthesis has been widely adopted in zero-
shot speech synthesis. However, they require a large-scale data and possess the same …

Although diffusion models in text-to-speech have become a popular choice due to their
strong generative ability, the intrinsic complexity of sampling from diffusion models harms …

Recent progress in large-scale zero-shot speech synthesis has been significantly advanced
by language models and diffusion models. However, the generation process of both …

In text-to-speech (TTS) synthesis, diffusion models have achieved promising generation
quality. However, because of the pre-defined data-to-noise diffusion process, their prior …

Audio language models have recently emerged as a promising approach for various audio
generation tasks, relying on audio tokenizers to encode waveforms into sequences of …

Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the
forefront of various generative tasks. However, their iterative sampling process poses a …

The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-
based generative models have demonstrated excellent performance in speech synthesis …