# Audio language models and spoken dialogue Area: [Speech and audio language models](https://mlsanity.com/speech/index.md). HTML: https://mlsanity.com/speech/audio-language-models-and-spoken-dialogue/ ## Key facts - Audio language models and spoken dialogue: 739 papers on arXiv since 2021 (data through 19 Oct 2026). - 200 of its 739 mapped papers (27%) cite “Qwen2-Audio Technical Report” (2024, arXiv 2407.10759). - 191 of its 739 mapped papers (26%) cite “Moshi: a speech-text foundation model for real-time dialogue” (2024, arXiv 2410.00037). - 28 new papers 2 Oct–19 Oct. ## Most cited here - [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024), cited by 200 papers here - [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024), cited by 191 papers here - [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023), cited by 187 papers here - [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023), cited by 158 papers here - [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025), cited by 136 papers here - [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024), cited by 135 papers here - [Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities](https://mlsanity.com/paper/2402.01831/) (2024), cited by 103 papers here - [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025), cited by 93 papers here - [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024), cited by 92 papers here - [GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities](https://mlsanity.com/paper/2406.11768/) (2024), cited by 91 papers here ## New (2 Oct–19 Oct) - [AudioScorer: Learning Question-Aware Token Relevance for Large Audio Language Models](https://mlsanity.com/paper/2610.26258/) (2026-10-19) - [Probing and Mitigating Hallucinations in Speech-augmented Language Models for Automatic Speech Recognition via Small Language Models](https://mlsanity.com/paper/2610.25351/) (2026-10-18) - [Pronouncing Hard Words: Phoneme Adaptation of a Pretrained Conversational Text to Speech Model](https://mlsanity.com/paper/2610.24164/) (2026-10-16) - [VocalGrad: Evaluating Acoustic Perception in Audio Language Models](https://mlsanity.com/paper/2610.23745/) (2026-10-16) - [ConvexLLM: Scaling Convex-Hull Speech Interfaces to General-Purpose Audio Intelligence](https://mlsanity.com/paper/2610.23539/) (2026-10-16) - [TRACE: Trustworthy Reasoning from Acoustic Cues and Evidence](https://mlsanity.com/paper/2610.26894/) (2026-10-15) - [Qwen-Audio-Jev: A Unified Interface for Audio Decisions](https://mlsanity.com/paper/2610.21614/) (2026-10-15) - [Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models](https://mlsanity.com/paper/2610.20763/) (2026-10-14) - [MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue](https://mlsanity.com/paper/2610.20172/) (2026-10-14) - [What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities](https://mlsanity.com/paper/2610.19476/) (2026-10-14) - [PhonoVoxtLM: Exploring Single-Codebook Phonological Tokens for Speech Understanding and Generation](https://mlsanity.com/paper/2610.18469/) (2026-10-13) - [Full-duplex Spoken Language Modeling with Discrete Diffusion](https://mlsanity.com/paper/2610.17780/) (2026-10-13) - [DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?](https://mlsanity.com/paper/2610.17738/) (2026-10-13) - [D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones](https://mlsanity.com/paper/2610.17124/) (2026-10-12) - [RefTAG: Reflection-aware Temporal Audio Grounding in Large Audio Language Models](https://mlsanity.com/paper/2610.16217/) (2026-10-12) - [Frontend-Assisted Large Audio-Language Models for SLT2026 SmartGlasses Challenge](https://mlsanity.com/paper/2610.13282/) (2026-10-09) - [SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty](https://mlsanity.com/paper/2610.13081/) (2026-10-09) - [STEMMA: Song-to-Stem Multi-Audio Reasoning for Large Audio Language Models](https://mlsanity.com/paper/2610.11884/) (2026-10-08) - [Selective Listening: Mechanism-Guided Control of Audio Influence in Large Audio-Language Models](https://mlsanity.com/paper/2610.11196/) (2026-10-08) - [MiDashengLM-Spatial: Unifying General Audio Understanding and Spatial Awareness](https://mlsanity.com/paper/2610.11156/) (2026-10-08) - [SmoothConv and DuplexConv: Complementary Mandarin Multi-Party Conversational Speech Corpora for Speech Interaction](https://mlsanity.com/paper/2610.11150/) (2026-10-08) - [BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics](https://mlsanity.com/paper/2610.10663/) (2026-10-07) - [Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented Languages](https://mlsanity.com/paper/2610.09467/) (2026-10-07) - [Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models](https://mlsanity.com/paper/2610.08125/) (2026-10-06) - [PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue](https://mlsanity.com/paper/2610.07725/) (2026-10-06) - [SkillFormer: Skill-Decomposed Adaptation for Audio Language Models](https://mlsanity.com/paper/2610.07533/) (2026-10-06) - [AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models](https://mlsanity.com/paper/2610.06949/) (2026-10-03) - [Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition](https://mlsanity.com/paper/2610.04683/) (2026-10-03)