English
Related papers

Related papers: Solla: Towards a Speech-Oriented LLM That Hears Ac…

200 papers

While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…

Computation and Language · Computer Science 2025-05-28 Jinwu Hu , Zhitian Zhang , Guohao Chen , Xutao Wen , Chao Shuai , Wei Luo , Bin Xiao , Yuanqing Li , Mingkui Tan

Understanding emotion from speech requires sensitivity to both lexical and acoustic cues. However, it remains unclear whether large audio language models (LALMs) genuinely process acoustic information or rely primarily on lexical content.…

Computation and Language · Computer Science 2025-10-20 Jingyi Chen , Zhimeng Guo , Jiyun Chun , Pichao Wang , Andrew Perrault , Micha Elsner

Natural Language Processing (NLP) and Voice Recognition agents are rapidly evolving healthcare by enabling efficient, accessible, and professional patient support while automating grunt work. This report serves as my self project wherein…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-21 Kabir Kumar

We present Large Sign Language Models (LSLM), a novel framework for translating 3D American Sign Language (ASL) by leveraging Large Language Models (LLMs) as the backbone, which can benefit hearing-impaired individuals' virtual…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Sen Zhang , Xiaoxiao He , Di Liu , Zhaoyang Xia , Mingyu Zhao , Chaowei Tan , Vivian Li , Bo Liu , Dimitris N. Metaxas , Mubbasir Kapadia

The Speaker Diarization and Recognition (SDR) task aims to predict "who spoke when and what" within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems.…

Sound · Computer Science 2026-01-06 Han Yin , Yafeng Chen , Chong Deng , Luyao Cheng , Hui Wang , Chao-Hong Tan , Qian Chen , Wen Wang , Xiangang Li

This paper presents Audio-Visual LLM, a Multimodal Large Language Model that takes both visual and auditory inputs for holistic video understanding. A key design is the modality-augmented training, which involves the integration of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Fangxun Shu , Lei Zhang , Hao Jiang , Cihang Xie

Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential. A standard serving practice concatenates the full dialogue history at every turn,…

Computation and Language · Computer Science 2026-05-13 Xueqi Cheng , Qiong Wu , Zhengyi Zhou , Xugui Zhou , Tyler Derr , Yushun Dong

Large language models (LLMs) have revolutionized the landscape of Natural Language Processing systems, but are computationally expensive. To reduce the cost without sacrificing performance, previous studies have explored various approaches…

Computation and Language · Computer Science 2024-10-01 Chia-Hsuan Lee , Hao Cheng , Mari Ostendorf

Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…

Sound · Computer Science 2025-07-29 Shaowen Wang , Xinyuan Chen , Yao Xu

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Jeong Hun Yeo , Hyeongseop Rha , Se Jin Park , Yong Man Ro

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-28 Xulin Fan , Vishal Sunder , Samuel Thomas , Mark Hasegawa-Johnson , Brian Kingsbury , George Saon

Language models require tokenized inputs. However, tokenization strategies for continuous data like audio and vision are often based on simple heuristics such as fixed sized convolutions or discrete clustering, which do not necessarily…

Computation and Language · Computer Science 2024-10-08 Alan Baade , Puyuan Peng , David Harwath

Recent advances in large language models (LLMs) and multimodal LLMs (MLLMs) have led to strong reasoning ability across a wide range of tasks. However, their ability to perform mathematical reasoning from spoken input remains underexplored.…

Computation and Language · Computer Science 2025-05-22 Chengwei Wei , Bin Wang , Jung-jae Kim , Nancy F. Chen

Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption that the SSL…

Sound · Computer Science 2025-06-17 Tony Alex , Sara Ahmed , Armin Mustafa , Muhammad Awais , Philip JB Jackson

Audio Large Language Models (Audio LLMs) enable human-like conversation about music, yet it is unclear if they are truly listening to the audio or just using textual reasoning, as recent benchmarks suggest. This paper investigates this…

Machine Learning · Computer Science 2026-05-18 Giovana Morais , Magdalena Fuentes

As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-to-text translation (ST) and other downstream tasks,…

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

Computation and Language · Computer Science 2025-08-20 Duygu Altinok

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-14 Kento Nozawa , Takashi Masuko , Toru Taniguchi

Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To…

Artificial Intelligence · Computer Science 2026-03-23 Jiaqi Xiong , Yunjia Qi , Qi Cao , Yu Zheng , Yutong Zhang , Ziteng Wang , Ruofan Liao , Weisheng Xu , Sichen Liu

Large-scale pre-trained image-text models exhibit robust multimodal representations, yet applying the Contrastive Language-Image Pre-training (CLIP) model to audio-visual localization remains challenging. Replacing the classification token…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Khanh Binh Nguyen , Chae Jung Park