{"total":111,"rows":[{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204,"area":null},{"id":"2412.00733","title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","created":"2024-12-01","cited_by_count":122,"area":"diffusion"},{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120,"area":"diffusion"},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80,"area":null},{"id":"2402.08021","title":"Careless Whisper: Speech-to-Text Hallucination Harms","created":"2024-02-12","cited_by_count":53,"area":null},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36,"area":"diffusion"},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27,"area":null},{"id":"2409.01754","title":"Empirical evidence of Large Language Model's influence on human spoken communication","created":"2024-09-03","cited_by_count":27,"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":"2501.15907","title":"Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation","created":"2025-01-27","cited_by_count":20,"area":null},{"id":"2511.23475","title":"AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement","created":"2025-11-28","cited_by_count":20,"area":null},{"id":"2506.16381","title":"InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems","created":"2025-06-19","cited_by_count":17,"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":"2411.10193","title":"DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2505.03054","title":"BLAB: Brutally Long Audio Bench","created":"2025-05-05","cited_by_count":11,"area":null},{"id":"2501.01384","title":"OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios","created":"2025-01-02","cited_by_count":9,"area":"synth"},{"id":"2502.14892","title":"EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2506.18623","title":"Efficient and Robust Speaker Diarization via Structured Pruning of Self-Supervised Models","created":"2025-06-23","cited_by_count":7,"area":"distill"},{"id":"2401.02839","title":"Pheme: Efficient and Conversational Speech Generation","created":"2024-01-05","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":"2502.07096","title":"Lotus: Creating Short Videos From Long Videos With Abstractive and Extractive Summarization","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2407.01777","title":"Deepfake Audio Detection Using Spectrogram-based Feature and Ensemble of Deep Learning Models","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2508.20474","title":"Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2601.06896","title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding","created":"2026-01-11","cited_by_count":5,"area":null},{"id":"2406.07890","title":"Exploring Speech Foundation Models for Speaker Diarization in Child-Adult Dyadic Interactions","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2406.15284","title":"The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data","created":"2024-06-21","cited_by_count":4,"area":null},{"id":"2409.00819","title":"LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2409.06991","title":"1M-Deepfakes Detection Challenge","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2410.06459","title":"Mamba-based Segmentation Model for Speaker Diarization","created":"2024-10-09","cited_by_count":4,"area":"ssm"},{"id":"2412.11896","title":"Classification of Spontaneous and Scripted Speech for Multilingual Audio","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2505.18436","title":"Voice of a Continent: Mapping Africa's Speech Technology Frontier","created":"2025-05-24","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":"2409.09135","title":"Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2410.03930","title":"Reverb: Open-Source ASR and Diarization from Rev","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2503.16578","title":"SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2506.11074","title":"Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2507.16136","title":"SDBench: A Comprehensive Benchmark Suite for Speaker Diarization","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2510.00499","title":"MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2601.11329","title":"F-Actor: Controllable Conversational Behaviour in Full-Duplex Models","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","cited_by_count":2,"area":null},{"id":"2407.04444","title":"TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2407.15828","title":"J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2409.12042","title":"ASR Benchmarking: Need for a More Representative Conversational Dataset","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2502.01402","title":"Annotation Tool and Dataset for Fact-Checking Podcasts","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2508.02000","title":"Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2509.26177","title":"Benchmarking Diarization Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2511.00256","title":"NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2601.19194","title":"SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2401.12850","title":"End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2406.13842","title":"Joint vs Sequential Speaker-Role Detection and Automatic Speech Recognition for Air-traffic Control","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2406.18679","title":"Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2407.03809","title":"Finetuning End-to-End Models for Estonian Conversational Spoken Language Translation","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2407.17477","title":"Toward Automated Detection of Biased Social Signals from the Content of Clinical Conversations","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2409.15885","title":"On the calibration of powerset speaker diarization models","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2505.19119","title":"CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2506.11344","title":"Do We Still Need Audio? Rethinking Speaker Diarization with a Text-Based Approach Using Multiple Prediction Models","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2507.06812","title":"Democratizing High-Fidelity Co-Speech Gesture Video Generation","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2509.00094","title":"Automatic Pronunciation Error Detection and Correction of the Holy Quran's Learners Using Deep Learning","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2510.00485","title":"PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2511.22696","title":"Probabilistic Fusion and Calibration of Neural Speaker Diarization Models","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2603.05450","title":"Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic Asymmetry","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.14794","title":"Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.27800","title":"CuriosAI Submission to the CASTLE Challenge at EgoVis 2026","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.16807","title":"Connecting Speech to Words through Images","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2609.15128","title":"Omni-Streaming Thinking","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2403.17314","title":"Project MOSLA: Recording Every Moment of Second Language Acquisition","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2407.10266","title":"psifx -- Psychological and Social Interactions Feature Extraction Package","created":"2024-07-14","cited_by_count":0,"area":null},{"id":"2409.08103","title":"The Faetar Benchmark: Speech Recognition in a Very Under-Resourced Language","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2412.00760","title":"Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment","created":"2024-12-01","cited_by_count":0,"area":null},{"id":"2412.17998","title":"WavePulse: Real-time Content Analytics of Radio Livestreams","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2502.05729","title":"BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2502.12714","title":"Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2503.11743","title":"PUBLICSPEAK: Hearing the Public with a Probabilistic Framework in Local Government","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2505.22054","title":"Voice Adaptation for Swiss German","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.02610","title":"Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2507.10311","title":"Recognizing Dementia from Neuropsychological Tests with State Space Models","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.13563","title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2601.19945","title":"Benchmarking von ASR-Modellen im deutschen medizinischen Kontext: Eine Leistungsanalyse anhand von Anamnesegespr\\\"achen","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2602.03245","title":"Mi\\'{c}i Princ -- A Little Boy Teaching Speech Technologies the Chakavian Dialect","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.07978","title":"Cross-Linguistic Persona-Driven Data Synthesis for Robust Multimodal Cognitive Decline Detection","created":"2026-02-08","cited_by_count":0,"area":"synth"},{"id":"2602.19991","title":"Cross-lingual Matryoshka Representation Learning across Speech and Text","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2602.21741","title":"Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.01622","title":"More Data, Fewer Diacritics: Scaling Arabic TTS","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.19256","title":"ShobdoSetu: A Data-Centric Framework for Bengali Long-Form Speech Recognition and Speaker Diarization","created":"2026-02-25","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":"2604.12700","title":"MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.15923","title":"Hierarchical Codec Diffusion for Video-to-Speech Generation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.26676","title":"A Toolkit for Detecting Spurious Correlations in Speech Datasets","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.08214","title":"Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.17370","title":"CBT-Audio: Evaluating Audio Language Models for Patient-Side Distress Intensity Estimation in CBT Session Recordings","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.22732","title":"Beyond Acoustic Emotion Recognition: Multimodal Pathos Analysis in Political Speech Using LLM-Based and Acoustic Emotion Models","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.23420","title":"Naturalistic measure of social norms alignment","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.27258","title":"PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.29765","title":"MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.00986","title":"Automatic Detection of Stress from Speech in the Trier Social Stress Test","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.12468","title":"An Omnilingual-ASR-Based Speech-LLM System for the 2nd MLC-SLM Challenge","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.18076","title":"Modeling turn-taking with distant viewing: investigating silence thresholds in human and AI-generated discourse","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.26249","title":"A large-scale corpus of religious radio broadcast transcripts from webstream recordings in the United States","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.01724","title":"TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.12549","title":"StrAD: A Streaming Method and Benchmark for Audio Description Generation for Long-form Videos","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":"100"}