Cover Image

Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Ruitao, Zhang, Bixi, Liang, Sheng, Yuan, Zheng
Format:	Preprint
Published:	2025
Subjects:	Sound I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models
by: Christop, Iwona, et al.
Published: (2026)

PathBench: Speech Intelligibility Benchmark for Automatic Pathological Speech Assessment
by: Halpern, Bence Mark, et al.
Published: (2026)

Advancing Expert Specialization for Better MoE
by: Guo, Hongcan, et al.
Published: (2025)

Multi-level SSL Feature Gating for Audio Deepfake Detection
by: Tran, Hoan My, et al.
Published: (2025)

Domain Adaptation of the Pyannote Diarization Pipeline for Conversational Indonesian Audio
by: Prasetyo, Muhammad Daffa'i Rafi, et al.
Published: (2026)

Curveball Steering: The Right Direction To Steer Isn't Always Linear
by: Raval, Shivam, et al.
Published: (2026)

Representation Loss Minimization with Randomized Selection Strategy for Efficient Environmental Fake Audio Detection
by: Phukan, Orchid Chetia, et al.
Published: (2024)

XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference
by: Vankov, Daniil, et al.
Published: (2026)

WhisperAlign: Word-Boundary-Aware ASR and WhisperX-Anchored Pyannote Diarization for Long-Form Bengali Speech
by: Chowdhury, Aurchi, et al.
Published: (2026)

BlasBench: An Open Benchmark for Irish Speech Recognition
by: Raj, Jyoutir, et al.
Published: (2026)

Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models
by: Tian, Changxin, et al.
Published: (2025)

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
by: Lasby, Mike, et al.
Published: (2025)

ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features
by: Lin, Ye Bhone, et al.
Published: (2025)

Self-Improvement for Audio Large Language Model using Unlabeled Speech
by: Wang, Shaowen, et al.
Published: (2025)

Step-Audio-R1 Technical Report
by: Tian, Fei, et al.
Published: (2025)

Evaluating Voice Command Pipelines for Drone Control: From STT and LLM to Direct Classification and Siamese Networks
by: Simões, Lucca Emmanuel Pineli, et al.
Published: (2024)

MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector
by: Costa-jussà, Marta R., et al.
Published: (2024)

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
by: Klerings, Alina, et al.
Published: (2025)

SpeechAccentLLM: A Unified Framework for Foreign Accent Conversion and Text to Speech
by: Cheng, Zhuangfei, et al.
Published: (2025)

Evaluating Steering Techniques using Human Similarity Judgments
by: Studdiford, Zach, et al.
Published: (2025)

Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution
by: Phukan, Orchid Chetia, et al.
Published: (2024)

SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset
by: Gautam, Sushant, et al.
Published: (2024)

Domain-Incremental Continual Learning for Robust and Efficient Keyword Spotting in Resource Constrained Systems
by: Dhungana, Prakash, et al.
Published: (2026)

Quantifying the effect of speech pathology on automatic and human speaker verification
by: Halpern, Bence Mark, et al.
Published: (2024)

Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models
by: Lee, Yejin, et al.
Published: (2026)

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio
by: Basha, Maris, et al.
Published: (2025)

Empathy Omni: Enabling Empathetic Speech Response Generation through Large Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Detecting and Steering LLMs' Empathy in Action
by: Cadile, Juan P.
Published: (2025)

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2025)

Predicting Upcoming Stuttering Events from Three-Second Audio: Stratified Evaluation Reveals Severity-Selective Precursors, and the Model Deploys Fully On-Device
by: Kozak, Nazar
Published: (2026)

Measuring Robustness of Speech Recognition from MEG Signals Under Distribution Shift
by: Chien, Sheng-You, et al.
Published: (2026)

Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model
by: Wang, Zihao, et al.
Published: (2025)

Assessing Latency in ASR Systems: A Methodological Perspective for Real-Time Use
by: Arriaga, Carlos, et al.
Published: (2024)

Multi-Reward GRPO for Stable and Prosodic Single-Codebook TTS LLMs at Scale
by: Zhong, Yicheng, et al.
Published: (2025)

Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization
by: Chowdhury, MD. Sagor, et al.
Published: (2026)

Probing neural audio codecs for distinctions among English nuclear tunes
by: Vigneaux, Juan Pablo, et al.
Published: (2026)

LLaMA-Omni: Seamless Speech Interaction with Large Language Models
by: Fang, Qingkai, et al.
Published: (2024)

Beyond Deep Learning: Speech Segmentation and Phone Classification with Neural Assemblies
by: Adelson, Trevor, et al.
Published: (2026)

Generation of Musical Timbres using a Text-Guided Diffusion Model
by: Yuan, Weixuan, et al.
Published: (2025)

Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models
by: Wen, Zhihao, et al.
Published: (2025)