Awesome-Speech-Language-Model
June 7, 2026 ยท View on GitHub
Awesome-Speech-Language-Model
Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.
Universal Speech, Audio and Music Understanding
Model
- LTU: Listen, Think, and Understand -
ICLR 2024 - SALMONN: Towards Generic Hearing Abilities for Large Language Models -
ICLR 2024 - LTU-AS: Joint Audio and Speech Understanding -
ASRU 2024 - Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models -
arXiv 2023 - Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities -
ICML 2024 - Qwen2-Audio Technical Report -
arXiv 2024 - WavLLM: Towards Robust and Adaptive Speech Large Language Model -
EMNLP 2024 - DiVA: Distilling an End-to-End Voice Assistant Without Instruction Training Data -
arXiv 2024 - SenseVoice: Multilingual Speech Understanding with Multi-Task Speech Foundation Model -
arXiv 2024
Benchmark
- Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech -
ICASSP 2024 - AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension -
ACL 2024 - SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words -
arXiv 2024 - AudioBench: A Universal Benchmark for Audio Large Language Models -
arXiv 2024 - SALMon: A Suite for Acoustic Language Model Evaluation -
arXiv 2024 - MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark -
arXiv 2024 - Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks -
ICLR 2024 open review - MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix -
NeurIPS 2025
End2End Speech Dialogue System
Model
- SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities -
EMNLP 2023 - GPT-4o Voice Mode -
API 2024 - PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems -
EMNLP 2024 - VITA: Towards Open-Source Interactive Omni Multimodal LLM -
arXiv 2024 - Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming -
arXiv 2024 - LLaMA-Omni: Seamless Speech Interaction with Large Language Models -
arXiv 2024 - Moshi: a speech-text foundation model for real-time dialogue -
arXiv 2024 - Westlake-Omni -
GitHub 2024 - EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions -
arXiv 2024 - IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities -
arXiv 2024 - Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities -
arXiv 2024 - MooER-omni -
GitHub 2024 - GLM-4-Voice -
GitHub 2024 - Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM -
arXiv 2024 - Hertz-dev -
GitHub 2024 - Fish Agent -
GitHub 2024 - KE-Omni: Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
arXiv 2024
Benchmark
- VoiceBench: Benchmarking LLM-Based Voice Assistants -
arXiv 2024
Full Duplex Modeling
- A Full-duplex Speech Dialogue Scheme Based On Large Language Models -
NeurIPS 2024 - MiniCPM-duplex: Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models -
EMNLP 2024 - LSLM: Language Model Can Listen While Speaking -
arXiv 2024 - SyncLLM: Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents -
arXiv 2024 - Enabling Real-Time Conversations with Minimal Training Costs -
arXiv 2024
Survey
- Towards audio language modeling -- an overview -
arXiv 2024 - Recent Advances in Speech Language Models: A Survey -
arXiv 2024 - A Survey on Speech Large Language Models -
arXiv 2024 - Speech Trident -
Github