English
Related papers

Related papers: TSPE: Task-Specific Prompt Ensemble for Improved Z…

200 papers

By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However, task performance depends significantly on the quality of the prompt used to steer…

Machine Learning · Computer Science 2023-03-13 Yongchao Zhou , Andrei Ioan Muresanu , Ziwen Han , Keiran Paster , Silviu Pitis , Harris Chan , Jimmy Ba

Target sound extraction (TSE) aims to extract the sound part of a target sound event class from a mixture audio with multiple sound events. The previous works mainly focus on the problems of weakly-labelled data, jointly learning and new…

Sound · Computer Science 2022-04-05 Helin Wang , Dongchao Yang , Chao Weng , Jianwei Yu , Yuexian Zou

Open-vocabulary audio-language models, like CLAP, offer a promising approach for zero-shot audio classification (ZSAC) by enabling classification with any arbitrary set of categories specified with natural language prompts. In this paper,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Sreyan Ghosh , Sonal Kumar , Chandra Kiran Reddy Evuru , Oriol Nieto , Ramani Duraiswami , Dinesh Manocha

Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, fine-grained image classification remains challenging. It demands precise attention to subtle visual details to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Yunqi Hong , Sohyun An , Andrew Bai , Neil Y. C. Lin , Cho-Jui Hsieh

Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xin Wang , Yixu Wang , Jiaming Zhang , Ruofan Wang , Jiaqi Yu , Kai Chen , Jingjing Chen , Xingjun Ma , Yu-Gang Jiang

How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…

Computation and Language · Computer Science 2023-05-29 Xuandong Zhao , Siqi Ouyang , Zhiguo Yu , Ming Wu , Lei Li

Audio-visual target speaker extraction (AV-TSE) models primarily rely on target visual cues to isolate the target speaker's voice from others. We know that humans leverage linguistic knowledge, such as syntax and semantics, to support…

Sound · Computer Science 2025-06-17 Wenxuan Wu , Shuai Wang , Xixin Wu , Helen Meng , Haizhou Li

In recent years, dynamic parameterization of acoustic environments has garnered attention in audio processing. This focus includes room volume and reverberation time (RT60), which define local acoustics independent of sound source and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Chunxi Wang , Maoshen Jia , Meiran Li , Changchun Bao , Wenyu Jin

Audio-Language Models (ALMs) are making strides in understanding speech and non-speech audio. However, domain-specialist Foundation Models (FMs) remain the best for closed-ended speech processing tasks such as Speech Emotion Recognition…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-25 Saurabh Kataria , Xiao Hu

We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data. Specifically, we designed CALM to retrieve the probability distribution of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Jinhua Liang , Xubo Liu , Haohe Liu , Huy Phan , Emmanouil Benetos , Mark D. Plumbley , Wenwu Wang

Audio-Language Models (ALMs), trained on paired audio-text data, are designed to process, understand, and reason about audio-centric multimodal content. Unlike traditional supervised approaches that use predefined labels, ALMs leverage…

Sound · Computer Science 2026-03-13 Yi Su , Jisheng Bai , Qisheng Xu , Kele Xu , Yong Dou

Recently, zero-shot text-to-speech (TTS) systems, capable of synthesizing any speaker's voice from a short audio prompt, have made rapid advancements. However, the quality of the generated speech significantly deteriorates when the audio…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-11 Xiaofei Wang , Sefik Emre Eskimez , Manthan Thakker , Hemin Yang , Zirun Zhu , Min Tang , Yufei Xia , Jinzhu Li , Sheng Zhao , Jinyu Li , Naoyuki Kanda

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module,…

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…

A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting. However, while highly coveted and being the most general,…

Computation and Language · Computer Science 2023-10-24 Xingchen Wan , Ruoxi Sun , Hootan Nakhost , Hanjun Dai , Julian Martin Eisenschlos , Sercan O. Arik , Tomas Pfister

Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based "Think step by step" approaches, the field has evolved in two main…

Computation and Language · Computer Science 2025-07-25 Andreea Nica , Ivan Zakazov , Nicolas Mario Baldwin , Saibo Geng , Robert West

Audio-Language Models (ALM) aim to be general-purpose audio models by providing zero-shot capabilities at test time. The zero-shot performance of ALM improves by using suitable text prompts for each domain. The text prompts are usually…

Sound · Computer Science 2024-07-23 Soham Deshmukh , Rita Singh , Bhiksha Raj

Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Manli Shu , Weili Nie , De-An Huang , Zhiding Yu , Tom Goldstein , Anima Anandkumar , Chaowei Xiao

We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We selected three tasks: audio-visual speech recognition (AVSR), code-switched speech…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-17 Puyuan Peng , Brian Yan , Shinji Watanabe , David Harwath

Combining multiple machine learning models into an ensemble is known to provide superior performance levels compared to the individual components forming the ensemble. This is because models can complement each other in taking better…

Sound · Computer Science 2021-06-09 Nicolae-Catalin Ristea , Radu Tudor Ionescu