English
Related papers

Related papers: SAO-Instruct: Free-form Audio Editing using Natura…

200 papers

We introduce Bonito, an open-source model for conditional task generation that converts unannotated text into task-specific training datasets for instruction tuning. We aim to enable zero-shot task adaptation of large language models on…

Computation and Language · Computer Science 2024-09-12 Nihal V. Nayak , Yiyang Nan , Avi Trost , Stephen H. Bach

Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solely on end-to-end reasoning, limiting interpretability and accuracy for tasks that require structured…

Sound · Computer Science 2025-10-14 Kuan-Yi Lee , Tsung-En Lin , Hung-Yi Lee

Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master language but also solve…

Computation and Language · Computer Science 2023-06-16 Yew Ken Chia , Pengfei Hong , Lidong Bing , Soujanya Poria

Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits. To address this, we propose a novel…

Software Engineering · Computer Science 2022-09-15 Jiyang Zhang , Sheena Panthaplackel , Pengyu Nie , Junyi Jessy Li , Milos Gligoric

Recent AIGC systems possess the capability to generate digital multimedia content based on human language instructions, such as text, image and video. However, when it comes to speech, existing methods related to human instruction-to-speech…

Sound · Computer Science 2024-08-29 Yixuan Zhou , Xiaoyu Qin , Zeyu Jin , Shuoyi Zhou , Shun Lei , Songtao Zhou , Zhiyong Wu , Jia Jia

Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-10 David Xu

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

Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Zhefan Rao , Bin Zou , Haoxuan Che , Xuanhua He , Chong Hou Choi , Yanheng Li , Rui Liu , Qifeng Chen

The ability to provide fine-grained control for generating and editing visual imagery has profound implications for computer vision and its applications. Previous works have explored extending controllability in two directions: instruction…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Shufan Li , Harkanwar Singh , Aditya Grover

Audio language models process audio inputs using textual prompts for tasks like speech recognition and audio captioning. Although built on multilingual pre-trained components, most are trained primarily on English, limiting their usability…

Computation and Language · Computer Science 2025-05-26 Potsawee Manakul , Guangzhi Sun , Warit Sirichotedumrong , Kasima Tharnpipitchai , Kunat Pipatanakul

Modern computing students often rely on both natural-language prompting and manual code editing to solve programming tasks. Yet we still lack a clear understanding of how these two modes are combined in practice, and how their usage varies…

Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the…

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

The goal of audio captioning is to translate input audio into its description using natural language. One of the problems in audio captioning is the lack of training data due to the difficulty in collecting audio-caption pairs by crawling…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-15 Yuma Koizumi , Yasunori Ohishi , Daisuke Niizumi , Daiki Takeuchi , Masahiro Yasuda

Given an original image, image editing aims to generate an image that align with the provided instruction. The challenges are to accept multimodal inputs as instructions and a scarcity of high-quality training data, including crucial…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Zhen Han , Chaojie Mao , Zeyinzi Jiang , Yulin Pan , Jingfeng Zhang

Stutter removal is an essential scenario in the field of speech editing. However, when the speech recording contains stutters, the existing text-based speech editing approaches still suffer from: 1) the over-smoothing problem in the edited…

Sound · Computer Science 2023-05-24 Ziyue Jiang , Qian Yang , Jialong Zuo , Zhenhui Ye , Rongjie Huang , Yi Ren , Zhou Zhao

Existing deep learning (DL) based speech enhancement approaches are generally optimised to minimise the distance between clean and enhanced speech features. These often result in improved speech quality however they suffer from a lack of…

Sound · Computer Science 2021-11-19 Tassadaq Hussain , Mandar Gogate , Kia Dashtipour , Amir Hussain

Audio-text models trained via contrastive learning offer a practical approach to perform audio classification through natural language prompts, such as "this is a sound of" followed by category names. In this work, we explore alternative…

Sound · Computer Science 2024-09-23 Michel Olvera , Paraskevas Stamatiadis , Slim Essid

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

Computation and Language · Computer Science 2020-02-17 Marco Dinarelli , Nikita Kapoor , Bassam Jabaian , Laurent Besacier

Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research summaries needing comprehensive outputs. Current approaches…

Computation and Language · Computer Science 2025-11-04 Adewale Akinfaderin , Shreyas Subramanian , Akarsha Sehwag