English
Related papers

Related papers: Training Audio Captioning Models without Audio

200 papers

Audio captioning is the novel task of general audio content description using free text. It is an intermodal translation task (not speech-to-text), where a system accepts as an input an audio signal and outputs the textual description (i.e.…

Sound · Computer Science 2019-10-22 Konstantinos Drossos , Samuel Lipping , Tuomas Virtanen

Natural language is widely used to describe, prompt, and control audio systems, but rarely serves as the representation carrying audio itself. We introduce lexical acoustic coding (LAC), a framework in which pre-trained LLM sender and…

Machine Learning · Computer Science 2026-05-12 Emanuele Rossi , Emanuele Rodolà

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

Image captioning has emerged as an interesting research field in recent years due to its broad application scenarios. The traditional paradigm of image captioning relies on paired image-caption datasets to train the model in a supervised…

Computation and Language · Computer Science 2022-02-08 Jiahui Gao , Yi Zhou , Philip L. H. Yu , Shafiq Joty , Jiuxiang Gu

Audio-language pretraining holds promise for general-purpose audio understanding, yet remains underexplored compared to its vision counterpart. While vision-language models like CLIP serve as widely adopted foundations, existing…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-24 Wei-Cheng Tseng , Xuanru Zhou , Mingyue Huo , Yiwen Shao , Hao Zhang , Dong Yu

Contrastive cross-modal models such as CLIP and CLAP aid various vision-language (VL) and audio-language (AL) tasks. However, there has been limited investigation of and improvement in their language encoder, which is the central component…

Computation and Language · Computer Science 2023-10-23 Mengjie Zhao , Junya Ono , Zhi Zhong , Chieh-Hsin Lai , Yuhta Takida , Naoki Murata , Wei-Hsiang Liao , Takashi Shibuya , Hiromi Wakaki , Yuki Mitsufuji

We introduce ParaSpeechCLAP, a dual-encoder contrastive model that maps speech and text style captions into a common embedding space, supporting a wide range of intrinsic (speaker-level) and situational (utterance-level) descriptors (such…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-31 Anuj Diwan , Eunsol Choi , David Harwath

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

Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning. As an alternative to large models, we present SmallCap, which generates a caption…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Rita Ramos , Bruno Martins , Desmond Elliott , Yova Kementchedjhieva

Image captioning is a challenging computer vision task, which aims to generate a natural language description of an image. Most recent researches follow the encoder-decoder framework which depends heavily on the previous generated words for…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Zeliang Song , Xiaofei Zhou , Zhendong Mao , Jianlong Tan

We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent encoder and multiple speaker-dependent decoders. The…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-13 Orhan Ocal , Oguz H. Elibol , Gokce Keskin , Cory Stephenson , Anil Thomas , Kannan Ramchandran

This paper introduces a novel approach to speech restoration by integrating a context-related conditioning strategy. Specifically, we employ the diffusion-based generative restoration model, UNIVERSE++, as a backbone to evaluate the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-13 Soo-Whan Chung , Min-Seok Choi

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…

Computation and Language · Computer Science 2023-11-14 Fatema Hasan , Yulong Li , James Foulds , Shimei Pan , Bishwaranjan Bhattacharjee

The Controllable Image Captioning (CIC) task aims to generate captions conditioned on designated control signals. Several structure-related control signals are proposed to control the semantic structure of sentences, such as sentence length…

Artificial Intelligence · Computer Science 2021-11-23 Zhangzi Zhu , Tianlei Wang , Hong Qu

We live in a rich and varied acoustic world, which is experienced by individuals or communities as a soundscape. Computational auditory scene analysis, disentangling acoustic scenes by detecting and classifying events, focuses on objective…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-26 Yuanbo Hou , Qiaoqiao Ren , Andrew Mitchell , Wenwu Wang , Jian Kang , Tony Belpaeme , Dick Botteldooren

It is highly desirable yet challenging to generate image captions that can describe novel objects which are unseen in caption-labeled training data, a capability that is evaluated in the novel object captioning challenge (nocaps). In this…

Computer Vision and Pattern Recognition · Computer Science 2021-03-08 Xiaowei Hu , Xi Yin , Kevin Lin , Lijuan Wang , Lei Zhang , Jianfeng Gao , Zicheng Liu

Language-audio joint representation learning frameworks typically depend on deterministic embeddings, assuming a one-to-one correspondence between audio and text. In real-world settings, however, the language-audio relationship is…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-22 Toranosuke Manabe , Yuchi Ishikawa , Hokuto Munakata , Tatsuya Komatsu

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Computation and Language · Computer Science 2020-11-05 Stéphane d'Ascoli , Alice Coucke , Francesco Caltagirone , Alexandre Caulier , Marc Lelarge

Multimodal pre-training for audio-and-text has recently been proved to be effective and has significantly improved the performance of many downstream speech understanding tasks. However, these state-of-the-art pre-training audio-text models…

Sound · Computer Science 2022-04-12 Yu Kang , Tianqiao Liu , Hang Li , Yang Hao , Wenbiao Ding

Large audio-language models (LALMs), built upon powerful Large Language Models (LLMs), have exhibited remarkable audio comprehension and reasoning capabilities. However, the training of LALMs demands a large corpus of audio-language pairs,…

Sound · Computer Science 2026-01-15 Wen Wang , Ruibing Hou , Hong Chang , Shiguang Shan , Xilin Chen