{"total":105,"rows":[{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"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":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100,"area":null},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"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":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2301.00591","title":"Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling","created":"2023-01-02","cited_by_count":47,"area":null},{"id":"2503.01174","title":"Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics","created":"2025-03-03","cited_by_count":47,"area":null},{"id":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","cited_by_count":45,"area":null},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34,"area":null},{"id":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","cited_by_count":28,"area":null},{"id":"2305.19269","title":"Make-A-Voice: Unified Voice Synthesis With Discrete Representation","created":"2023-05-30","cited_by_count":27,"area":null},{"id":"2505.17060","title":"SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation","created":"2025-05-17","cited_by_count":27,"area":null},{"id":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25,"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":"2411.07111","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","created":"2023-10-08","cited_by_count":19,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2512.14865","title":"Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction","created":"2025-12-16","cited_by_count":19,"area":null},{"id":"2503.14345","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","created":"2025-03-18","cited_by_count":18,"area":null},{"id":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17,"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":"2404.06690","title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations","created":"2024-04-10","cited_by_count":15,"area":null},{"id":"2509.22243","title":"FLEXI: Benchmarking Full-duplex Human-LLM Speech Interaction","created":"2025-09-26","cited_by_count":15,"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":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2509.26388","title":"Game-Time: Evaluating Temporal Dynamics in Spoken Language Models","created":"2025-09-30","cited_by_count":13,"area":null},{"id":"2604.12928","title":"MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models","created":"2026-04-14","cited_by_count":12,"area":null},{"id":"2305.11435","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","created":"2023-05-19","cited_by_count":11,"area":null},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2509.02521","title":"FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training","created":"2025-09-02","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":"2509.14515","title":"From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models","created":"2025-09-18","cited_by_count":10,"area":null},{"id":"2305.08709","title":"Back Translation for Speech-to-text Translation Without Transcripts","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","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":"2408.11849","title":"Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation","created":"2024-08-13","cited_by_count":7,"area":null},{"id":"2510.02327","title":"KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2603.09180","title":"DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization","created":"2026-03-10","cited_by_count":7,"area":null},{"id":"2608.25218","title":"TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue","created":"2026-08-25","cited_by_count":7,"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":"2501.00805","title":"SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation","created":"2025-01-01","cited_by_count":6,"area":null},{"id":"2603.17837","title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2410.15017","title":"DM-Codec: Distilling Multimodal Representations for Speech Tokenization","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2506.02979","title":"Towards a Japanese Full-duplex Spoken Dialogue System","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2607.06540","title":"Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs","created":"2026-07-07","cited_by_count":5,"area":null},{"id":"2312.15197","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","created":"2023-12-23","cited_by_count":4,"area":null},{"id":"2505.17446","title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.00267","title":"CASPER: A Large Scale Spontaneous Speech Dataset","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2507.20091","title":"ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models","created":"2025-07-27","cited_by_count":4,"area":null},{"id":"2303.05431","title":"disco: a toolkit for Distributional Control of Generative Models","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2412.17292","title":"AV-EmoDialog: Chat with Audio-Visual Users Leveraging Emotional Cues","created":"2024-12-23","cited_by_count":3,"area":null},{"id":"2510.12210","title":"DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2603.16874","title":"Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2607.04941","title":"DuplexChat: Constructing Speaker-Separated Full-Duplex Dialogue Speech at Scale for Spoken Dialogue Language Modeling","created":"2026-07-06","cited_by_count":3,"area":null},{"id":"2607.29125","title":"M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models","created":"2026-07-31","cited_by_count":3,"area":null},{"id":"2608.10878","title":"X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction","created":"2026-08-11","cited_by_count":3,"area":null},{"id":"2403.14808","title":"A Collection of Pragmatic-Similarity Judgments over Spoken Dialog Utterances","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2507.18161","title":"Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2507.18897","title":"HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2601.19786","title":"Rethinking Discrete Speech Representation Tokens for Accent Generation","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2605.20356","title":"Synchronization and Turn-Taking in Full-Duplex Speech Dialogue Models","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.21970","title":"Integrating Facial Generation into Full-Duplex Spoken Dialogue Systems","created":"2026-06-20","cited_by_count":2,"area":null},{"id":"2608.26005","title":"VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction","created":"2026-08-26","cited_by_count":2,"area":null},{"id":"2301.11316","title":"Open Problems in Applied Deep Learning","created":"2023-01-26","cited_by_count":1,"area":null},{"id":"2406.06251","title":"Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2407.01911","title":"Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2508.07375","title":"TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2508.11224","title":"Benchmarking Prosody Encoding in Discrete Speech Tokens","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2510.06673","title":"Heptapod: Language Modeling on Visual Signals","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2512.20296","title":"TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2603.07025","title":"Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2603.08179","title":"Privacy-Preserving End-to-End Full-Duplex Speech Dialogue Models","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.12350","title":"TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.22267","title":"TiCo: Time-Controllable Spoken Dialogue Model","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.07467","title":"Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yor\\`ub\\'a","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.30256","title":"VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.00168","title":"RealityTest: How People Probe AI Identity and Whether Models Disclose It","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2609.08147","title":"ConversationalVoice: Full-Duplex Speech Data from Real Conversations through Source-Faithful Reconstruction and Conversation-Grounded Expansion","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.19596","title":"Full-Duplex Speech Models Take the Floor When Asked, Not When Needed","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2402.01298","title":"Learning Semantic Information from Raw Audio Signal Using Both Contextual and Phonetic Representations","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2405.18669","title":"Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2505.14356","title":"PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2512.01865","title":"Cross-Lingual Interleaving for Speech Language Models","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.08233","title":"Tutti: Expressive Multi-Singer Synthesis via Structure-Level Timbre Control and Vocal Texture Modeling","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.23295","title":"Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.10199","title":"How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2609.04288","title":"Scalable Context Orchestration for Serving LLMs Over Voice","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07200","title":"KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.12623","title":"SteerDuplex: Steerable Duplex Speech Dialogue Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.13117","title":"Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.13893","title":"Lie to me: Detecting Managerial Evasiveness in Earnings Calls via Conversational Audio Encoders","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":"100"}