English
Related papers

Related papers: FxSearcher: gradient-free text-driven audio transf…

200 papers

LLM-based automatic speech recognition models demonstrate strong performance by connecting audio encoders and LLMs. However, data scarcity of paired speech and transcription often hinders their adaptation to new domains, making text-only…

Sound · Computer Science 2026-05-15 Ryo Magoshi , Takashi Maekaku , Yusuke Shinohara

Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint…

Sound · Computer Science 2021-02-11 Sungkyun Chang , Donmoon Lee , Jeongsoo Park , Hyungui Lim , Kyogu Lee , Karam Ko , Yoonchang Han

Language-queried audio source separation (LASS) focuses on separating sounds using textual descriptions of the desired sources. Current methods mainly use discriminative approaches, such as time-frequency masking, to separate target sounds…

Sound · Computer Science 2025-01-10 Yi Yuan , Xubo Liu , Haohe Liu , Mark D. Plumbley , Wenwu Wang

Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users…

Computation and Language · Computer Science 2024-12-17 Shahar Elisha , Andrew McDowell , Mariano Beguerisse-Díaz , Emmanouil Benetos

As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ensemble has attracted…

Computation and Language · Computer Science 2023-08-24 Chenrui Zhang , Lin Liu , Jinpeng Wang , Chuyuan Wang , Xiao Sun , Hongyu Wang , Mingchen Cai

In zero-shot text-to-speech, achieving a balance between fidelity to the target speaker and adherence to text content remains a challenge. While classifier-free guidance (CFG) strategies have shown promising results in image generation,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-25 John Zheng , Farhad Maleki

Prompt tuning has emerged as a lightweight strategy for adapting foundation models to downstream tasks, particularly for resource-constrained systems. As pre-trained prompts become valuable assets, combining multiple source prompts offers a…

Computation and Language · Computer Science 2025-10-16 Enming Zhang , Liwen Cao , Yanru Wu , Zijie Zhao , Yang Li

We propose a method of separating a desired sound source from a single-channel mixture, based on either a textual description or a short audio sample of the target source. This is achieved by combining two distinct models. The first model,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-13 Kevin Kilgour , Beat Gfeller , Qingqing Huang , Aren Jansen , Scott Wisdom , Marco Tagliasacchi

Recent advances in audio declipping have substantially improved the state of the art.% in certain saturation regimes. Yet, practitioners need guidelines to choose a method, and while existing benchmarks have been instrumental in advancing…

Sound · Computer Science 2020-12-01 Clément Gaultier , Srđan Kitić , Rémi Gribonval , Nancy Bertin

Recent breakthroughs in language-queried audio source separation (LASS) have shown that generative models can achieve higher separation audio quality than traditional masking-based approaches. However, two key limitations restrict their…

Classifier-free guidance (CFG) is a cornerstone of text-to-image diffusion models, yet its effectiveness is limited by the use of static guidance scales. This "one-size-fits-all" approach fails to adapt to the diverse requirements of…

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…

We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD method using prompt…

Sound · Computer Science 2024-10-15 Hideyuki Oiso , Yuto Matsunaga , Kazuya Kakizaki , Taiki Miyagawa

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically \textit{heterogeneous},…

Automated Audio Captioning (AAC) generates captions for audio clips but faces challenges due to limited datasets compared to image captioning. To overcome this, we propose the zero-shot AAC system that leverages pre-trained models,…

Computation and Language · Computer Science 2025-09-17 Vijay Govindarajan , Pratik Patel , Sahil Tripathi , Md Azizul Hoque , Gautam Siddharth Kashyap

Sound effects play an essential role in producing high-quality radio stories but require enormous labor cost to add. In this paper, we address the problem of automatically adding sound effects to radio stories with a retrieval-based model.…

Information Retrieval · Computer Science 2019-08-22 Songwei Ge , Curtis Xuan , Ruihua Song , Chao Zou , Wei Liu , Jin Zhou

We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…

Sound · Computer Science 2017-08-03 Volodymyr Kuleshov , S. Zayd Enam , Stefano Ermon

Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a…

Sound · Computer Science 2024-06-10 Manjie Xu , Chenxing Li , Duzhen zhang , Dan Su , Wei Liang , Dong Yu

Prompt tuning, in which prompts are optimized to adapt large-scale pre-trained language models to downstream tasks instead of fine-tuning the full model parameters, has been shown to be particularly effective when the prompts are trained in…

Computation and Language · Computer Science 2024-02-14 Haeju Lee , Minchan Jeong , Se-Young Yun , Kee-Eung Kim

Video Multimethod Assessment Fusion (VMAF) [1], [2], [3] is a popular tool in the industry for measuring coded video quality. In this study, we propose an auditory-inspired frontend in existing VMAF for creating videos of reference and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-08 Arijit Biswas , Harald Mundt