Related papers: SoundStorm: Efficient Parallel Audio Generation

We propose a general feedback-driven retrieval-augmented generation (RAG) approach that leverages Large Audio Language Models (LALMs) to address the missing or imperfect synthesis of specific sound events in text-to-audio (TTA) generation.…

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…

In this paper, we propose PhantomSound, a query-efficient black-box attack toward voice assistants. Existing black-box adversarial attacks on voice assistants either apply substitution models or leverage the intermediate model output to…

While contemporary speech separation technologies adeptly process lengthy mixed audio waveforms, they are frequently challenged by the intricacies of real-world environments, including noisy and reverberant settings, which can result in…

Generating combined visual and auditory sensory experiences is critical for the consumption of immersive content. Recent advances in neural generative models have enabled the creation of high-resolution content across multiple modalities…

Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming…

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

We introduce SeeingSounds, a lightweight and modular framework for audio-to-image generation that leverages the interplay between audio, language, and vision-without requiring any paired audio-visual data or training on visual generative…

Foley sound generation, the art of creating audio for multimedia, has recently seen notable advancements through text-conditioned latent diffusion models. These systems use multimodal text-audio representation models, such as Contrastive…

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…

While diffusion and autoregressive (AR) models have significantly advanced generative modeling, they each present distinct limitations. AR models, which rely on causal attention, cannot exploit future context and suffer from slow generation…

Audio-LLM introduces audio modality into a large language model (LLM) to enable a powerful LLM to recognize, understand, and generate audio. However, during speech recognition in noisy environments, we observed the presence of illusions and…

Recent multi-modal video generation models have achieved high visual quality, but their prohibitive latency and limited temporal stability hinder real-time deployment. Streaming inference exacerbates these issues, leading to pronounced…

We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and…

In recent years, Text-to-Audio Generation has achieved remarkable progress, offering sound creators powerful tools to transform textual inspirations into vivid audio. However, existing models predominantly operate directly in the acoustic…

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive…

Text-to-audio systems, while increasingly performant, are slow at inference time, thus making their latency unpractical for many creative applications. We present Adversarial Relativistic-Contrastive (ARC) post-training, the first…

We present a controlled empirical comparison between autoregressive (AR) and masked diffusion (MDLM) language models. Both models are trained on identical data (50M tokens from TinyStories), identical compute budget (20,000 steps, batch…

Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…

Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound…