{"total":77,"rows":[{"id":"2310.13025","title":"Powerset multi-class cross entropy loss for neural speaker diarization","created":"2023-10-19","cited_by_count":111,"area":null},{"id":"2402.08021","title":"Careless Whisper: Speech-to-Text Hallucination Harms","created":"2024-02-12","cited_by_count":53,"area":null},{"id":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2308.10897","title":"Can Language Models Learn to Listen?","created":"2023-08-21","cited_by_count":40,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26,"area":null},{"id":"2306.13734","title":"The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios","created":"2023-06-23","cited_by_count":22,"area":null},{"id":"2309.07525","title":"SingFake: Singing Voice Deepfake Detection","created":"2023-09-14","cited_by_count":21,"area":null},{"id":"2408.14080","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","created":"2024-08-26","cited_by_count":21,"area":null},{"id":"2405.18346","title":"Intelligent Clinical Documentation: Harnessing Generative AI for Patient-Centric Clinical Note Generation","created":"2024-05-28","cited_by_count":20,"area":null},{"id":"2410.04527","title":"Casablanca: Data and Models for Multidialectal Arabic Speech Recognition","created":"2024-10-06","cited_by_count":20,"area":null},{"id":"2306.04428","title":"Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages","created":"2023-06-07","cited_by_count":18,"area":null},{"id":"2212.12137","title":"Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing","created":"2022-12-23","cited_by_count":17,"area":null},{"id":"2306.03789","title":"On the Robustness of Arabic Speech Dialect Identification","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2401.02746","title":"Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2206.02432","title":"Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2209.04167","title":"Overlapped speech and gender detection with WavLM pre-trained features","created":"2022-09-09","cited_by_count":6,"area":null},{"id":"2401.05314","title":"ANIM-400K: A Large-Scale Dataset for Automated End-To-End Dubbing of Video","created":"2024-01-10","cited_by_count":6,"area":null},{"id":"2408.07448","title":"LiveFC: A System for Live Fact-Checking of Audio Streams","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2312.03231","title":"Deep Multimodal Fusion for Surgical Feedback Classification","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2501.12640","title":"Toxicity Begets Toxicity: Unraveling Conversational Chains in Political Podcasts","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2503.02389","title":"Robust detection of overlapping bioacoustic sound events","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2505.13036","title":"KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025","created":"2025-05-19","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":"2202.13826","title":"Magnitude-aware Probabilistic Speaker Embeddings","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2311.14836","title":"Custom Data Augmentation for low resource ASR using Bark and Retrieval-Based Voice Conversion","created":"2023-11-24","cited_by_count":3,"area":null},{"id":"2604.08125","title":"PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2302.02742","title":"Residual Information in Deep Speaker Embedding Architectures","created":"2023-02-06","cited_by_count":2,"area":null},{"id":"2303.12002","title":"End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations","created":"2023-03-21","cited_by_count":2,"area":null},{"id":"2307.13012","title":"Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains","created":"2023-07-24","cited_by_count":2,"area":null},{"id":"2311.00697","title":"End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2402.00067","title":"Online speaker diarization of meetings guided by speech separation","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2410.11068","title":"Character-aware audio-visual subtitling in context","created":"2024-10-14","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":"2509.26177","title":"Benchmarking Diarization Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2306.00680","title":"Encoder-decoder multimodal speaker change detection","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2308.02160","title":"Speaker Diarization of Scripted Audiovisual Content","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2401.08268","title":"An Explainable Proxy Model for Multiabel Audio Segmentation","created":"2024-01-16","cited_by_count":1,"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":"2402.13152","title":"AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2406.17124","title":"Investigating Confidence Estimation Measures for Speaker Diarization","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2407.04280","title":"LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2407.04293","title":"Systematic Evaluation of Online Speaker Diarization Systems Regarding their Latency","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2409.09340","title":"Egocentric Speaker Classification in Child-Adult Dyadic Interactions: From Sensing to Computational Modeling","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2410.11434","title":"Titanic Calling: Low Bandwidth Video Conference from the Titanic Wreck","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2502.18285","title":"Uncertainty Modeling in Multimodal Speech Analysis Across the Psychosis Spectrum","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2504.18950","title":"Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustness","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2505.23207","title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2509.25503","title":"DeepFake Detection in Dyadic Video Calls using Point of Gaze Tracking","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2604.16767","title":"When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2205.07086","title":"Collar-aware Training for Streaming Speaker Change Detection in Broadcast Speech","created":"2022-05-14","cited_by_count":0,"area":null},{"id":"2209.11906","title":"Joint Speech Activity and Overlap Detection with Multi-Exit Architecture","created":"2022-09-24","cited_by_count":0,"area":null},{"id":"2302.09991","title":"Towards Measuring and Scoring Speaker Diarization Fairness","created":"2023-02-20","cited_by_count":0,"area":null},{"id":"2306.04268","title":"Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2307.05171","title":"Enriching Verbal Feedback from Usability Testing: Automatic Linking of Thinking-Aloud Recordings and Stimulus using Eye Tracking and Mouse Data","created":"2023-07-11","cited_by_count":0,"area":null},{"id":"2309.13085","title":"Does My Dog ''Speak'' Like Me? The Acoustic Correlation between Pet Dogs and Their Human Owners","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2312.11512","title":"Path Signature Representation of Patient-Clinician Interactions as a Predictor for Neuropsychological Tests Outcomes in Children: A Proof of Concept","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2403.00212","title":"Transcription and translation of videos using fine-tuned XLSR Wav2Vec2 on custom dataset and mBART","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2406.13385","title":"Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2407.13408","title":"DISCOVER: A Data-driven Interactive System for Comprehensive Observation, Visualization, and ExploRation of Human Behaviour","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2502.17579","title":"VANPY: Voice Analysis Framework","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2504.18988","title":"LINC: Supporting Language Independent Communication and Comprehension to Enhance Contribution in Multilingual Collaborative Meetings","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2506.01365","title":"Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion","created":"2025-06-02","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":"2508.06393","title":"Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2510.15669","title":"Disentanglement of Sources in a Multi-Stream Variational Autoencoder","created":"2025-10-17","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":"2602.21741","title":"Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.02030","title":"TCG CREST System Description for the DISPLACE-M Challenge","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.03158","title":"An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization","created":"2026-03-03","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":"2604.15929","title":"MUSCAT: MUltilingual, SCientific ConversATion Benchmark","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2606.05931","title":"To Be Multimodal or Not to Be: Query-Adaptive Audio-Visual Person Retrieval via Active Modality Detection","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2610.01846","title":"Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?","created":"2026-10-01","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":"2610.04690","title":"SepRQ : Self-Supervised Speech Mixture Representation Learning via Mask-Free, Multi-Scale Source Separation","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}