Cover Image

Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Runyan, Si, Yuke, Gao, Yingying, Feng, Junlan, Deng, Chao, Zhang, Shilei
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Computation and Language Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HarmoniFuse: A Component-Selective and Prompt-Adaptive Framework for Multi-Task Speech Language Modeling
by: Si, Yuke, et al.
Published: (2025)

GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model
by: Gao, Yingying, et al.
Published: (2024)

PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models
by: Yang, Runyan, et al.
Published: (2024)

Plugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired by Dynamic Neural Network
by: Chen, Yanan, et al.
Published: (2024)

MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition
by: Sun, Haiyang, et al.
Published: (2023)

On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations
by: Hao, Yaqian, et al.
Published: (2024)

CEC: A Noisy Label Detection Method for Speaker Recognition
by: Shen, Yao, et al.
Published: (2024)

B-GRPO: Unsupervised Speech Emotion Recognition based on Batched-Group Relative Policy Optimization
by: Gao, Yingying, et al.
Published: (2026)

OneVoice: One Model, Triple Scenarios-Towards Unified Zero-shot Voice Conversion
by: Wang, Zhichao, et al.
Published: (2026)

Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection
by: Kheir, Yassine El, et al.
Published: (2025)

Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction
by: Li, Tianpeng, et al.
Published: (2025)

Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval
by: Zhou, Lifeng, et al.
Published: (2024)

USAD: Universal Speech and Audio Representation via Distillation
by: Chang, Heng-Jui, et al.
Published: (2025)

SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
by: Yang, Chih-Kai, et al.
Published: (2025)

AUDDT: Audio Unified Deepfake Detection Benchmark Toolkit
by: Zhu, Yi, et al.
Published: (2025)

Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification
by: Hao, Yaqian, et al.
Published: (2024)

Audios Don't Lie: Multi-Frequency Channel Attention Mechanism for Audio Deepfake Detection
by: Feng, Yangguang
Published: (2024)

Coarse-to-fine Alignment Makes Better Speech-image Retrieval
by: Zhou, Lifeng, et al.
Published: (2024)

Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding
by: Wang, Juncheng, et al.
Published: (2026)

What Are They Doing? Joint Audio-Speech Co-Reasoning
by: Wang, Yingzhi, et al.
Published: (2024)

DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
by: Liu, Jiaxuan, et al.
Published: (2024)

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators
by: Chen, Chen, et al.
Published: (2025)

Interpreting End-to-End Deep Learning Models for Speech Source Localization Using Layer-wise Relevance Propagation
by: Comanducci, Luca, et al.
Published: (2024)

Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model
by: Xue, Jinlong, et al.
Published: (2024)

Robust Audio Tagging under Class-wise Supervision Unreliability
by: Hou, Yuanbo, et al.
Published: (2026)

AUV: Teaching Audio Universal Vector Quantization with Single Nested Codebook
by: Chen, Yushen, et al.
Published: (2025)

Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning
by: Kuan, Chun-Yi, et al.
Published: (2024)

Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs
by: Zhang, Wenyu, et al.
Published: (2025)

AudioGenie-Reasoner: A Training-Free Multi-Agent Framework for Coarse-to-Fine Audio Deep Reasoning
by: Rong, Yan, et al.
Published: (2025)

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
by: Huang, Ailin, et al.
Published: (2025)

Layer-wise Analysis for Quality of Multilingual Synthesized Speech
by: Cooper, Erica, et al.
Published: (2025)

Exploring Text-Queried Sound Event Detection with Audio Source Separation
by: Yin, Han, et al.
Published: (2024)

MiMo-Audio: Audio Language Models are Few-Shot Learners
by: Core Team, et al.
Published: (2025)

Multimodal Magic Elevating Depression Detection with a Fusion of Text and Audio Intelligence
by: Gan, Lindy, et al.
Published: (2025)

MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
by: Huang, Hsiao-Ying, et al.
Published: (2025)

Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis
by: Chen, Yushen, et al.
Published: (2026)

STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
by: Liu, Zihan, et al.
Published: (2025)

Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples
by: Kuan, Chun-Yi, et al.
Published: (2025)

Covo-Audio Technical Report
by: Wang, Wenfu, et al.
Published: (2026)

To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation
by: Waheed, Abdul, et al.
Published: (2024)