Speech Large Language Models

Follow this topic Ask about this topic

Recent momentum

-9%

10 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

4 new papers

A weekly snapshot of new work published in Speech Large Language Models.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Speech Large Language Models.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Speech Large Language Models.

79 papers

Latest in Speech Large Language Models

Browse all topics →

A Unified and Reproducible Experimentation Framework for Speech Understanding
May 29, 2026Jing Peng, Junhao Du, Chenghao Wang +21Speech Large Language Models Reproducibility
MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables
May 28, 2026Sung-Lin Yeh, Wei Zhou, Gil Keren +6Speech Large Language Models Zero-Shot Text-To-Speech
TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition
May 27, 2026Xinyu Wang, Ziyu Zhao, Ke Bai +4Speech Large Language Models Weight-Only Quantization
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
May 24, 2026Yang Xiao, Siyi Wang, Eun-Jung Holden +1Discrete Speech Representations Acoustic Representation
Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM
May 7, 2026Wenqian Cui, Xiao-Hui Li, Daxin Tan +2Speech Large Language Models Speech Encoder
Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization
May 6, 2026Mohammed Aman Bhuiyan, Md Sazzad Hossain Adib, Samiul Basir Bhuiyan +4Speaker Diarization Speech Large Language Models
MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model
May 5, 2026Jingyao GongSpeech Large Language Models Small Language Models
Alethia: A Foundational Encoder for Voice Deepfakes
Apr 30, 2026Yi Zhu, Brahmi Dwivedi, Jayaram Raghuram +1Audio Deepfake Detection Deepfake Detection
Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?
Apr 30, 2026Yurii Halychanskyi, Nimet Beyza Bozdag, Mark Hasegawa-Johnson +2Speech Large Language Models Phoneme-Level Analysis
WhisperPipe: A Resource-Efficient Streaming Architecture for Real-Time Automatic Speech Recognition
Apr 28, 2026Erfan Ramezani, Mohammad Mahdi Giahi, Mohammad Erfan Zarabadipour +2Automatic Speech Recognition Systems Speech Large Language Models
Prompting Whisper for Joint Speech Transcription and Diarization
Apr 24, 2026Mariia Zamyrova, Henk van den HeuvelSpeaker Diarization Accurate Transcription
Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech
Apr 22, 2026Siqi Ouyang, Shuoyang Ding, Oleksii Hrinchuk +4Simultaneous Speech Translation Speech Translation
Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
Apr 21, 2026Jonas Waldendorf, Bashar Awwad Shiekh Hasan, Evgenii TsymbalovHallucination Detection Speech Large Language Models
Measuring the Redundancy of Decoder Layers in SpeechLLMs
Mar 5, 2026Adel Moumen, Guangzhi Sun, Philip C WoodlandSpeech Large Language Models Large Language Model Decoder
When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech
Mar 5, 2026Akif Islam, Raufun Nahar, Md. Ekramul HamidSpeech Separation Speech Enhancement
FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation
Jan 8, 2026Junseok Lee, Chang-Jae ChunSpeech Large Language Models Token Compression
Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption
Mar 21, 2025Xiang Li, Pin-Yu Chen, Wenqi WeiAudio Deepfake Detection Deepfake Detection
Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)
Date pendingPeidong Wang, Jian Xue, Jinyu LiSpeech Large Language Models Logit Lens
BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language
Date pendingMuhammad AliLibrispeech Speech Large Language Models

May 29, 2026 · eess.ASJ/K move · Enter open · S save

A Unified and Reproducible Experimentation Framework for Speech Understanding

Jing Peng, Junhao Du, Chenghao Wang, Hanqi Li+20

1X-LANCE Lab, Department of Computer Science and Engineering, Shanghai Jiao Tong University · 2AISpeech Ltd, Suzhou, China · 3ETH Zürich, Switzerland · 5Hangzhou Dianzi University, Hangzhou, China · 6The Chinese University of Hong Kong, Shenzhen, China

Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduces an agent-assisted training conversion flow that maps paper and code into versioned, runnable training pipelines under a unified protocol on matched open-data subsets. Overall, SURE improves comparability and reproducibility for deployment-oriented evaluation.

Speech Large Language Models Reproducibility

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

4 new papers

2 new papers

1 new paper

Latest in Speech Large Language Models