{"total":56,"rows":[{"id":"2604.24954","title":"Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence","created":"2026-04-27","cited_by_count":30,"area":null},{"id":"2512.16378","title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2605.19833","title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2512.17648","title":"Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2606.05121","title":"Audio Interaction Model","created":"2026-06-03","cited_by_count":4,"area":null},{"id":"2606.14647","title":"Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2604.10065","title":"ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2607.18934","title":"Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2604.07354","title":"Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wild","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2606.08194","title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2510.23320","title":"LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2602.22522","title":"Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.16545","title":"Symphony for Speech-to-Text: Supporting Real-Time Medical Voice Interfaces","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.10675","title":"Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.25460","title":"Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.29534","title":"Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2609.08390","title":"Noise Adaptive Streaming Audio-Visual Speech Token Enhancement for Robust Full-Duplex Spoken Dialogue Models","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2511.18774","title":"Zero-Shot Context-Aware ASR for Diverse Arabic Varieties","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.19161","title":"From Speech to Subtitles: Evaluating ASR Models in Subtitling Italian Television Programs","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2603.15326","title":"Tagarela - A Portuguese speech dataset from podcasts","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.16924","title":"SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.25750","title":"Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models","created":"2026-03-20","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":"2605.01496","title":"SF20K Competition 2025: Summary and findings","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.07705","title":"Encoder-Decoder Transformers: Logical Characterizations and Periodicity","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.28833","title":"Transcribing Children's Speech: ASR Performance and Obtaining Reliable Orthographic Transcriptions","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2606.03948","title":"A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.04418","title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.08486","title":"TRADE: Transducer-Augmented Decoder for Speech LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.15984","title":"ROMPAR: Morphological Completion and Demographic Unlearning for Romanian-Accented Speech Recognition","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.17255","title":"MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.18319","title":"ASTRA: A Scalable Next-Generation ATCO Training Simulator with Autonomous Simpilots","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.26968","title":"RedVox: Safety and Fairness Gaps in Speech Models Across Languages","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.31112","title":"What Counts as an Error? Dual-Reference Benchmarking for Atypical ASR","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.02138","title":"The Role of Disfluencies in Speech Translation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.18117","title":"Position: AI Leaderboards Are Underserving the Global South: A Case Study from India","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.21853","title":"PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.11786","title":"Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13498","title":"Building a Production Greek-English Speech Recognizer","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.16614","title":"RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.18673","title":"Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.21084","title":"The Hidden Cost of Digits: Number Normalization and WER in ASR Systems","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21844","title":"Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.29418","title":"Controlling Backchannels in Streamable Full-duplex Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.29448","title":"YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32560","title":"How to Reduce Whisper Hallucination","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35645","title":"CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36920","title":"Benchmarking Automatic Speech Recognition Tools for Iberian Languages","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00154","title":"How Robust Are Neural Audio Codecs for African Speech? A Multi-Task Benchmark and the Limits of Perceptual Quality","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2610.03017","title":"Personalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial Conversations","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09916","title":"NeuralZip: Reusable Setup for Fast Lossless Compression","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10145","title":"InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviews","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11646","title":"Phonologically Informed Tokenization for German Speech Recognition: A Cross-Domain Study","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14299","title":"RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14643","title":"AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}