paper-with-me

홈 › Papers

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders

2025-02-21 · Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, Jingbo Zhu

Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC). Most research focuses on training an adapter layer to generate a unified audio feature for the LLM. However, different tasks may require distinct features that emphasize either semantic or acoustic aspects, making task-specific audio features more desirable. In this paper, we propose Prompt-aware Mixture (PaM) to enhance the Speech LLM that uses multiple audio encoders. Our approach involves using different experts to extract different features based on the prompt that indicates different tasks. Experiments demonstrate that with PaM, only one Speech LLM surpasses the best performances achieved by all single-encoder Speech LLMs on ASR, Speaker Number Verification, and AC tasks. PaM also outperforms other feature fusion baselines, such as concatenation and averaging.

📄 PDF Abstract BibTeX arXiv:2502.15178

Code (0)

등록된 구현이 없습니다.

Tasks

Audio captioningAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

An Investigation of Large Language Models for Real-World Hate Speech Detection

2024-01-07 · Keyan Guo, Alexander Hu, Jaden Mu, Ziheng Shi 외

Hate speech has emerged as a major problem plaguing our social spaces today. While there have been significant efforts to address this problem, existing methods are still significantly limited in effectively detecting ha…

Hate Speech Detection

Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving

2025-05-24 · Jingran Xie, Xiang Li, Hui Wang, Yue Yu 외

Large language models (LLMs) have shown remarkable generalization across tasks, leading to increased interest in integrating speech with LLMs. These speech LLMs (SLLMs) typically use supervised fine-tuning to align speec…

Decoder

Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization

2024-12-27 · Kumud Tripathi, Raj Gothi, Pankaj Wasnik

Automatic speech recognition has recently seen a significant advancement with large foundational models such as Whisper. However, these models often struggle to perform well in low-resource languages, such as Indian lang…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition

AIVA: An AI-based Virtual Companion for Emotion-aware Interaction

2025-09-03 · Chenxi Li arxiv

Recent advances in Large Language Models (LLMs) have significantly improved natural language understanding and generation, enhancing Human-Computer Interaction (HCI). However, LLMs are limited to unimodal text processing…

Natural Language UnderstandingContrastive LearningPrompt Engineering

VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs

2026-03-09 · Hezhao Zhang, Huang-Cheng Chou, Shrikanth Narayanan, Thomas Hain arxiv

Speech Large Language Models (LLMs) show great promise for speech emotion recognition (SER) via generative interfaces. However, shifting from closed-set classification to open text generation introduces zero-shot stochas…

Speech Emotion RecognitionText Generation