相关论文: SoloAudio: Target Sound Extraction with Language-o…

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

This paper addresses unsupervised diffusion-based single-channel speech enhancement (SE). Prior work in this direction combines a score-based diffusion model trained on clean speech with a Gaussian noise model whose covariance is structured…

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect…

Speaker extraction is to extract a target speaker's voice from multi-talker speech. It simulates humans' cocktail party effect or the selective listening ability. The prior work mostly performs speaker extraction in frequency domain, then…

Speech enhancement significantly improves the clarity and intelligibility of speech in noisy environments, improving communication and listening experiences. In this paper, we introduce a novel pretraining feature-guided diffusion model…

Diffusion-based text-to-audio (TTA) generation has made substantial progress, leveraging latent diffusion model (LDM) to produce high-quality, diverse and instruction-relevant audios. However, beyond generation, the task of audio editing…

Audio editing is applicable for various purposes, such as adding background sound effects, replacing a musical instrument, and repairing damaged audio. Recently, some diffusion-based methods achieved zero-shot audio editing by using a…

The goal of speech enhancement (SE) is to eliminate the background interference from the noisy speech signal. Generative models such as diffusion models (DM) have been applied to the task of SE because of better generalization in unseen…

Spatial target speaker extraction isolates a desired speaker's voice in multi-speaker environments using spatial information, such as the direction of arrival (DoA). Although recent deep neural network (DNN)-based discriminative methods…

This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise. Our approach is based on generative inverse sampling, where we model clean speech and…

Recently, diffusion-based generative models have demonstrated remarkable performance in speech enhancement tasks. However, these methods still encounter challenges, including the lack of structural information and poor performance in low…

Humans can easily isolate a single speaker from a complex acoustic environment, a capability referred to as the "Cocktail Party Effect." However, replicating this ability has been a significant challenge in the field of target speaker…

Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as…

In this work, we propose Exformer, a time-domain architecture for target speaker extraction. It consists of a pre-trained speaker embedder network and a separator network based on transformer encoder blocks. We study multiple methods to…

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents…

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…

We present OmniVoice, a massively multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive (NAR) architecture. Unlike conventional…

Time-domain single-channel speech enhancement (SE) still remains challenging to extract the target speaker without any prior information on multi-talker conditions. It has been shown via auditory attention decoding that the brain activity…

Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces…