Related papers: IntMeanFlow: Few-step Speech Generation with Integ…

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 methods is slow and computationally intensive. Efficient speech…

The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements,…

We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without…

Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data…

Creating realistic, natural, and lip-readable talking face videos remains a formidable challenge. Previous research primarily concentrated on generating and aligning single-frame images while overlooking the smoothness of frame-to-frame…

The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reasoning. Our method, InterRS, tackles this by inserting reasoning steps only during natural…

Text-to-Speech (TTS) has recently seen great progress in synthesizing high-quality speech owing to the rapid development of parallel TTS systems, but producing speech with naturalistic prosodic variations, speaking styles and emotional…

Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While…

Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to use in real-time…

We propose a methodology for generating time-dependent turbulent inflow data with the aid of machine learning (ML), which has a possibility to replace conventional driver simulations or synthetic turbulent inflow generators. As for the ML…

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…

Diffusion Models have emerged as a leading class of generative models, yet their iterative sampling process remains computationally expensive. Timestep distillation is a promising technique to accelerate generation, but it often requires…

Existing DiT-based audio-driven avatar generation methods have achieved considerable progress, yet their broader application is constrained by limitations such as high computational overhead and the inability to synthesize long-duration…

Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adversarial Networks (GANs) have increasingly been used in…

Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative…

This paper introduces Interleaved Speech-Text Language Model (IST-LM) for zero-shot streaming Text-to-Speech (TTS). Unlike many previous approaches, IST-LM is directly trained on interleaved sequences of text and speech tokens with a fixed…

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion…

Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable…

Flow matching models have emerged as a powerful method for generative modeling on domains like images or videos, and even on irregular or unstructured data like 3D point clouds or even protein structures. These models are commonly trained…