{"total":72,"rows":[{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72,"area":"agents"},{"id":"2407.00837","title":"Towards Robust Speech Representation Learning for Thousands of Languages","created":"2024-06-30","cited_by_count":50,"area":null},{"id":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"area":null},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24,"area":null},{"id":"2411.01834","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","created":"2024-11-04","cited_by_count":23,"area":"alignment"},{"id":"2409.12403","title":"Preference Alignment Improves Language Model-Based TTS","created":"2024-09-19","cited_by_count":21,"area":"alignment"},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2406.16107","title":"Decoder-only Architecture for Streaming End-to-end Speech Recognition","created":"2024-06-23","cited_by_count":13,"area":null},{"id":"2410.03752","title":"Efficient Streaming LLM for Speech Recognition","created":"2024-10-02","cited_by_count":12,"area":null},{"id":"2403.12408","title":"MSLM-S2ST: A Multitask Speech Language Model for Textless Speech-to-Speech Translation with Speaker Style Preservation","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2407.15835","title":"dMel: Speech Tokenization made Simple","created":"2024-07-22","cited_by_count":11,"area":null},{"id":"2405.17809","title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2406.09345","title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2505.02707","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","created":"2025-05-05","cited_by_count":10,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2502.15218","title":"ESPnet-SpeechLM: An Open Speech Language Model Toolkit","created":"2025-02-21","cited_by_count":9,"area":"agents"},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2506.17611","title":"OpusLM: A Family of Open Unified Speech Language Models","created":"2025-06-21","cited_by_count":9,"area":null},{"id":"2401.09802","title":"Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2410.00025","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2503.10620","title":"From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2508.09350","title":"Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling","created":"2025-08-12","cited_by_count":7,"area":null},{"id":"2409.11274","title":"Task Arithmetic for Language Expansion in Speech Translation","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2410.15316","title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2410.17485","title":"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning","created":"2024-10-23","cited_by_count":6,"area":null},{"id":"2402.16021","title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages","created":"2024-02-25","cited_by_count":5,"area":null},{"id":"2406.06582","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2410.03007","title":"FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model","created":"2024-10-03","cited_by_count":5,"area":"inference"},{"id":"2410.20336","title":"Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation","created":"2024-10-27","cited_by_count":5,"area":null},{"id":"2411.06968","title":"Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition","created":"2024-11-11","cited_by_count":5,"area":"ssm"},{"id":"2506.10911","title":"NoLoCo: No-all-reduce Low Communication Training Method for Large Models","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2406.09618","title":"Multi-Modal Retrieval For Large Language Model Based Speech Recognition","created":"2024-06-13","cited_by_count":4,"area":"mllm"},{"id":"2407.03892","title":"On the Effectiveness of Acoustic BPE in Decoder-Only TTS","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2602.05220","title":"Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2602.16687","title":"Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2401.18045","title":"SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition","created":"2024-01-31","cited_by_count":3,"area":null},{"id":"2408.00624","title":"SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2501.06562","title":"Discrete Speech Unit Extraction via Independent Component Analysis","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2506.10299","title":"Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2509.14882","title":"Llama-Mimi: Exploring the Limits of Flattened Speech Language Modeling","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2510.15851","title":"SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2409.16654","title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","created":"2024-09-25","cited_by_count":2,"area":"mllm"},{"id":"2411.17690","title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2505.16691","title":"EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2506.23670","title":"Efficient Interleaved Speech Modeling through Knowledge Distillation","created":"2025-06-30","cited_by_count":2,"area":"distill"},{"id":"2507.19361","title":"SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models","created":"2025-07-25","cited_by_count":2,"area":"agents"},{"id":"2403.12402","title":"An Empirical Study of Speech Language Models for Prompt-Conditioned Speech Synthesis","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2410.13268","title":"Roadmap towards Superhuman Speech Understanding using Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2506.14767","title":"A Variational Framework for Improving Naturalness in Generative Spoken Language Models","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2509.05359","title":"An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2510.04593","title":"UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models","created":"2025-10-06","cited_by_count":1,"area":"diffusion"},{"id":"2603.05299","title":"WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2606.14786","title":"MatchLM2Lite: A Scalable MLLM-to-Lite Framework for Reproduced Content Identification","created":"2026-06-10","cited_by_count":1,"area":"distill"},{"id":"2606.22811","title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2409.09506","title":"ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2409.10969","title":"Enhancing Code-switched Text-to-Speech Synthesis Capability in Large Language Models with only Monolingual Corpora","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2506.17019","title":"Instituto de Telecomunica\\c{c}\\~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2606.12199","title":"Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2610.14349","title":"Multimodal Co-Generation With Continuous Bitstream Diffusion","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}