English
Related papers

Related papers: CLAPSep: Leveraging Contrastive Pre-trained Model …

200 papers

Text-guided sound separation enables flexible audio editing, assistive listening, and open-domain source extraction, but systems such as AudioSep remain too expensive for low-latency edge or codec-mediated deployment. Existing neural audio…

Sound · Computer Science 2026-04-28 Adhiraj Banerjee , Vipul Arora

Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language queries. In this paper, for the first time, we perform…

Target speaker extraction (TSE) aims to extract the speech of a target speaker from mixtures containing multiple competing speakers. Conventional TSE systems predominantly rely on speaker cues, such as pre-enrolled speech, to identify and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-10 Haoyu Li , Yu Xi , Yidi Jiang , Shuai Wang , Kate Knill , Mark Gales , Haizhou Li , Kai Yu

Machine hearing of the environmental sound is one of the important issues in the audio recognition domain. It gives the machine the ability to discriminate between the different input sounds that guides its decision making. In this work we…

Sound · Computer Science 2022-07-20 Peter Ochieng , Dennis Kaburu

We introduce CLaMP: Contrastive Language-Music Pre-training, which learns cross-modal representations between natural language and symbolic music using a music encoder and a text encoder trained jointly with a contrastive loss. To pre-train…

Sound · Computer Science 2023-10-19 Shangda Wu , Dingyao Yu , Xu Tan , Maosong Sun

Target speech extraction (TSE) extracts the speech of a target speaker in a mixture given auxiliary clues characterizing the speaker, such as an enrollment utterance. TSE addresses thus the challenging problem of simultaneously performing…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-15 Marc Delcroix , Keisuke Kinoshita , Tsubasa Ochiai , Katerina Zmolikova , Hiroshi Sato , Tomohiro Nakatani

In this paper, we investigate a novel approach for Target Speech Extraction (TSE), which relies solely on textual context to extract the target speech. We refer to this task as Contextual Speech Extraction (CSE). Unlike traditional TSE…

Sound · Computer Science 2025-03-13 Minsu Kim , Rodrigo Mira , Honglie Chen , Stavros Petridis , Maja Pantic

In recent years, exploring effective sound separation (SSep) techniques to improve overlapping sound event detection (SED) attracts more and more attention. Creating accurate separation signals to avoid the catastrophic error accumulation…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-07 Yunhao Liang , Yanhua Long , Yijie Li , Jiaen Liang

We propose listen to extract (LExt), a highly-effective while extremely-simple algorithm for monaural target speaker extraction (TSE). Given an enrollment utterance of a target speaker, LExt aims at extracting the target speaker from the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-06 Pengjie Shen , Kangrui Chen , Shulin He , Pengru Chen , Shuqi Yuan , He Kong , Xueliang Zhang , Zhong-Qiu Wang

Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt…

Sound · Computer Science 2025-04-04 Nishit Anand , Ashish Seth , Ramani Duraiswami , Dinesh Manocha

Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal…

Sound · Computer Science 2024-04-30 Yi Yuan , Zhuo Chen , Xubo Liu , Haohe Liu , Xuenan Xu , Dongya Jia , Yuanzhe Chen , Mark D. Plumbley , Wenwu Wang

In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Helin Wang , Jiarui Hai , Yen-Ju Lu , Karan Thakkar , Mounya Elhilali , Najim Dehak

As a practical alternative of speech separation, target speaker extraction (TSE) aims to extract the speech from the desired speaker using additional speaker cue extracted from the speaker. Its main challenge lies in how to properly extract…

Sound · Computer Science 2023-01-18 Kai Liu , Xucheng Wan , Ziqing Du , Huan Zhou

Target Speaker Extraction (TSE) aims to extract the clean speech of the target speaker in an audio mixture, eliminating irrelevant background noise and speech. While prior work has explored various auxiliary cues including pre-recorded…

Sound · Computer Science 2026-04-28 Ziyang Jiang , Jiahe Lei , Xueyan Chen , Yifan Zhang , Zexu Pan , Wei Xue , Xinyuan Qian

We introduce MMAudioSep, a generative model for video/text-queried sound separation that is founded on a pretrained video-to-audio model. By leveraging knowledge about the relationship between video/text and audio learned through a…

Sound · Computer Science 2026-04-20 Akira Takahashi , Shusuke Takahashi , Yuki Mitsufuji

Acoustic Word Embeddings (AWEs) improve the efficiency of speech retrieval tasks such as Spoken Term Detection (STD) and Keyword Spotting (KWS). However, existing approaches suffer from limitations, including unimodal supervision, disjoint…

Sound · Computer Science 2025-12-17 Ramesh Gundluru , Shubham Gupta , Sri Rama Murty K

Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and…

Binaural target sound extraction (TSE) aims to extract a desired sound from a binaural mixture of arbitrary sounds while preserving the spatial cues of the desired sound. Indeed, for many applications, the target sound signal and its…

Target speaker extraction (TSE) aims to isolate a specific speaker's voice from multi-speaker mixtures. Despite strong benchmark results, real-world performance often degrades due to different interacting factors. Previous curriculum…

Sound · Computer Science 2026-03-06 Yun Liu , Xuechen Liu , Xiaoxiao Miao , Junichi Yamagishi

Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background…

Sound · Computer Science 2024-01-09 Zizheng Zhang , Chen Chen , Hsin-Hung Chen , Xiang Liu , Yuchen Hu , Eng Siong Chng