Related papers: Sample-Efficient Diffusion for Text-To-Speech Synt…

We introduce DiffuseST, a low-latency, direct speech-to-speech translation system capable of preserving the input speaker's voice zero-shot while translating from multiple source languages into English. We experiment with the synthesizer…

We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy…

We present SALAD, a zero-shot TTS autoregressive model operating over continuous speech representations. SALAD utilizes a per-token diffusion process to refine and predict continuous representations for the next time step. We compare our…

A primary challenge when deploying speaker recognition systems in real-world applications is performance degradation caused by environmental mismatch. We propose a diffusion-based method that takes speaker embeddings extracted from a…

Text-to-speech synthesis (TTS) is a task to convert texts into speech. Two of the factors that have been driving TTS are the advancements of probabilistic models and latent representation learning. We propose a TTS method based on latent…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

The Semantic Layered Embedding Diffusion (SLED) mechanism redefines the representation of hierarchical semantics within transformer-based architectures, enabling enhanced contextual consistency across a wide array of linguistic tasks. By…

Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable advancements in fields…

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech…

Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due to its discrete…

There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory…

Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This…

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…

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on…

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training,…

Training a high performance end-to-end speech (E2E) processing model requires an enormous amount of labeled speech data, especially in the era of data-centric artificial intelligence. However, labeled speech data are usually scarcer and…

The aim of this project was to develop and implement an English language Text-to-Speech synthesis system. This involved a study of mechanisms of human speech production, a review of techniques in speech synthesis, and analysis of tests used…

In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without…