Cover Image

Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Yuan, Song, Jiaqi, Qiu, Guang, Wang, Xianliang, Lei, Ming, Gao, Jie, Wu, Jie
Format:	Preprint
Published:	2026
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

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
by: Xie, Yuan, et al.
Published: (2026)

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
by: Bai, Ye, et al.
Published: (2024)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
by: Tian, Wenjie, et al.
Published: (2026)

FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration
by: Xu, Kai-Tuo, et al.
Published: (2025)

Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text
by: Xue, Hongfei, et al.
Published: (2024)

Efficient Scaling for LLM-based ASR
by: Mu, Bingshen, et al.
Published: (2025)

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
by: Xue, Hongfei, et al.
Published: (2025)

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
by: Mu, Bingshen, et al.
Published: (2024)

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
by: Li, Longhao, et al.
Published: (2025)

Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding
by: Huo, Mingyue, et al.
Published: (2025)

Speech Emotion Recognition with ASR Integration
by: Li, Yuanchao
Published: (2026)

Dynamic Frequency-Adaptive Knowledge Distillation for Speech Enhancement
by: Yuan, Xihao, et al.
Published: (2025)

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
by: Wei, Linye, et al.
Published: (2025)

Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR
by: Shao, Mingchen, et al.
Published: (2025)

Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect
by: Mdhaffar, Salima, et al.
Published: (2024)

Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition
by: Xie, Xurong, et al.
Published: (2022)

Towards Robust Dysarthric Speech Recognition: LLM-Agent Post-ASR Correction Beyond WER
by: Zheng, Xiuwen, et al.
Published: (2026)

UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models
by: Fan, Ruchao, et al.
Published: (2024)

MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
by: Zhang, Bowen, et al.
Published: (2025)

Multi-Channel Differential ASR for Robust Wearer Speech Recognition on Smart Glasses
by: Yang, Yufeng, et al.
Published: (2025)

Comparative Analysis of ASR Methods for Speech Deepfake Detection
by: Salvi, Davide, et al.
Published: (2024)

Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR
by: Ma, Hao, et al.
Published: (2025)

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications
by: Pulikodan, Sujith, et al.
Published: (2025)

BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM
by: Gong, Xun, et al.
Published: (2025)

Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
by: Lin, Zhennan, et al.
Published: (2026)

ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark
by: Wang, He, et al.
Published: (2025)

Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches
by: Mujtaba, Dena, et al.
Published: (2025)

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
by: Wang, Weiqing, et al.
Published: (2024)

SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR
by: Guo, Pengcheng, et al.
Published: (2024)

SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models
by: Wang, Linqin, et al.
Published: (2024)

Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding
by: Jung, Yeonjoon, et al.
Published: (2024)

LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
by: Mu, Bingshen, et al.
Published: (2026)

DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching
by: Xie, Hanke, et al.
Published: (2025)

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
by: Shao, Mingchen, et al.
Published: (2025)

Elevating Robust Multi-Talker ASR by Decoupling Speaker Separation and Speech Recognition
by: Yang, Yufeng, et al.
Published: (2025)

BrainWhisperer: Leveraging Large-Scale ASR Models for Neural Speech Decoding
by: Boccato, Tommaso, et al.
Published: (2026)

SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
by: Deng, Keqi, et al.
Published: (2025)

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition
by: Mu, Bingshen, et al.
Published: (2025)

Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders
by: Violeta, Lester Phillip, et al.
Published: (2023)

EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed
by: Zhuang, Ziyang, et al.
Published: (2024)