{"total":24,"rows":[{"id":"2602.06053","title":"PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models","created":"2026-01-14","cited_by_count":63,"area":null},{"id":"2510.06961","title":"Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation","created":"2025-10-08","cited_by_count":23,"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":"2603.08823","title":"Fish Audio S2 Technical Report","created":"2026-03-09","cited_by_count":9,"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":"2602.11072","title":"Simultaneous Speech-to-Speech Translation Without Aligned Data","created":"2026-02-11","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":"2602.11298","title":"Voxtral Realtime","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2603.11123","title":"Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition","created":"2026-03-11","cited_by_count":6,"area":null},{"id":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.13518","title":"VoXtream2: Full-stream TTS with dynamic speaking rate control","created":"2026-03-13","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":"2603.11578","title":"Streaming Translation and Transcription Through Speech-to-Text Causal Alignment","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.11192","title":"Exploring Token-Space Manipulation in Latent Audio Tokenizers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.01016","title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2512.01865","title":"Cross-Lingual Interleaving for Speech Language Models","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2604.27543","title":"AppTek Call-Center Dialogues: A Multi-Accent Long-Form Benchmark for English ASR","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2609.08672","title":"X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.18333","title":"Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.28974","title":"Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.04333","title":"Factorized Delayed Streams Modeling for LLM-based Streaming ASR","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.07506","title":"Jarvis: A Proactive Speech Agent for Multi-Party Conversations","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}