相关论文: Fast Timing-Conditioned Latent Audio Diffusion

Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms…

General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separation models are either domain-specific, designed for fixed…

Robust spatial audio control relies on accurate acoustic propagation models, yet environmental variations, especially changes in the speed of sound, cause systematic mismatches that degrade performance. Existing methods either assume known…

Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…

Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been applied to compression, pushing the limits of continuous and…

We introduce an audio texture synthesis algorithm based on scattering moments. A scattering transform is computed by iteratively decomposing a signal with complex wavelet filter banks and computing their amplitude envelop. Scattering…

We introduce EzAudio, a text-to-audio (T2A) generation framework designed to produce high-quality, natural-sounding sound effects. Core designs include: (1) We propose EzAudio-DiT, an optimized Diffusion Transformer (DiT) designed for audio…

We introduce TangoFlux, an efficient Text-to-Audio (TTA) generative model with 515M parameters, capable of generating up to 30 seconds of 44.1kHz audio in just 3.7 seconds on a single A40 GPU. A key challenge in aligning TTA models lies in…

Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely,…

How does textual representation of audio relate to the Large Language Model's (LLMs) learning about the audio world? This research investigates the extent to which LLMs can be prompted to generate audio, despite their primary training in…

Current speech generation research can be categorized into two primary classes: non-autoregressive and autoregressive. The fundamental distinction between these approaches lies in the duration prediction strategy employed for…

Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still…

We introduce SRC-gAudio, a novel audio generation model designed to facilitate text-to-audio generation across a wide range of sampling rates within a single model architecture. SRC-gAudio incorporates the sampling rate as part of the…

Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and…

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to…

Video-to-audio (V2A) generation utilizes visual-only video features to produce realistic sounds that correspond to the scene. However, current V2A models often lack fine-grained control over the generated audio, especially in terms of…

Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. While recent studies…

This paper presents an energy-efficient stable diffusion processor for text-to-image generation. While stable diffusion attained attention for high-quality image synthesis results, its inherent characteristics hinder its deployment on…

Existing text-to-music models can produce high-quality audio with great diversity. However, textual prompts alone cannot precisely control temporal musical features such as chords and rhythm of the generated music. To address this…