{"total":24,"rows":[{"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":"2406.07096","title":"Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2602.11298","title":"Voxtral Realtime","created":"2026-02-11","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":"2412.13788","title":"Open Universal Arabic ASR Leaderboard","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2505.18609","title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2508.07014","title":"TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree","created":"2025-08-09","cited_by_count":4,"area":null},{"id":"2502.12408","title":"On the Robust Approximation of ASR Metrics","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2507.00534","title":"NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2511.03361","title":"Open Source State-Of-the-Art Solution for Romanian Speech Recognition","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2604.18105","title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.19079","title":"Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2607.06831","title":"Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2609.15759","title":"Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2602.24245","title":"Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2606.24169","title":"Data Scale, Not Latency, Shapes Cross-Lingual Encoder Transfer in Streaming ASR","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.18912","title":"From a Multilingual Streaming ASR Backbone to Kenyan-Language Systems: Data-Centric Adaptation of Nemotron 3.5 for Kikuyu, Dholuo, and Kalenjin","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.13717","title":"StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.14991","title":"Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.20995","title":"Voice-Light: A Full-Duplex Cascaded Voice Agent with Causal Turn-Taking and Speculative Generation","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30416","title":"All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation","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},{"id":"2610.13447","title":"O\\'ido: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}