{"total":79,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124,"area":null},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"area":null},{"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":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2303.04439","title":"A Light Weight Model for Active Speaker Detection","created":"2023-03-08","cited_by_count":40,"area":null},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36,"area":null},{"id":"2108.02607","title":"UniCon: Unified Context Network for Robust Active Speaker Detection","created":"2021-08-05","cited_by_count":28,"area":null},{"id":"2201.01928","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"area":null},{"id":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","cited_by_count":25,"area":null},{"id":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21,"area":null},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18,"area":null},{"id":"2309.12306","title":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","created":"2023-09-21","cited_by_count":16,"area":null},{"id":"2409.06656","title":"Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems","created":"2024-09-10","cited_by_count":15,"area":null},{"id":"2411.07076","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","created":"2024-11-11","cited_by_count":15,"area":"mllm"},{"id":"2206.10421","title":"Rethinking Audio-visual Synchronization for Active Speaker Detection","created":"2022-06-21","cited_by_count":9,"area":null},{"id":"2302.10248","title":"VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge","created":"2023-02-20","cited_by_count":9,"area":null},{"id":"2408.14886","title":"The VoxCeleb Speaker Recognition Challenge: A Retrospective","created":"2024-08-27","cited_by_count":9,"area":null},{"id":"2511.01169","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction","created":"2025-11-03","cited_by_count":9,"area":null},{"id":"2104.02878","title":"Three-class Overlapped Speech Detection using a Convolutional Recurrent Neural Network","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2401.12039","title":"Look, Listen and Recognise: Character-Aware Audio-Visual Subtitling","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2103.10661","title":"USTC-NELSLIP System Description for DIHARD-III Challenge","created":"2021-03-19","cited_by_count":7,"area":null},{"id":"2110.03361","title":"Multi-scale speaker embedding-based graph attention networks for speaker diarisation","created":"2021-10-07","cited_by_count":7,"area":null},{"id":"2203.15961","title":"Using Active Speaker Faces for Diarization in TV shows","created":"2022-03-30","cited_by_count":7,"area":null},{"id":"2208.13085","title":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization","created":"2022-08-27","cited_by_count":7,"area":null},{"id":"2302.12716","title":"Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2407.05608","title":"A Benchmark for Multi-speaker Anonymization","created":"2024-07-08","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":"2303.05321","title":"WASD: A Wilder Active Speaker Detection Dataset","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2501.11899","title":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","created":"2025-01-21","cited_by_count":6,"area":null},{"id":"2505.21954","title":"Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2210.14682","title":"In search of strong embedding extractors for speaker diarisation","created":"2022-10-26","cited_by_count":5,"area":null},{"id":"2412.08594","title":"ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection","created":"2024-12-11","cited_by_count":5,"area":null},{"id":"2104.02879","title":"Adapting Speaker Embeddings for Speaker Diarisation","created":"2021-04-07","cited_by_count":4,"area":null},{"id":"2109.00577","title":"FaVoA: Face-Voice Association Favours Ambiguous Speaker Detection","created":"2021-09-01","cited_by_count":4,"area":null},{"id":"2210.10985","title":"Large-scale learning of generalised representations for speaker recognition","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2311.12564","title":"Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environments","created":"2023-11-21","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":"2512.16250","title":"AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding","created":"2025-12-18","cited_by_count":4,"area":"mllm"},{"id":"2202.13826","title":"Magnitude-aware Probabilistic Speaker Embeddings","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2211.04304","title":"BER: Balanced Error Rate For Speaker Diarization","created":"2022-11-08","cited_by_count":3,"area":null},{"id":"2303.06806","title":"Neural Diarization with Non-autoregressive Intermediate Attractors","created":"2023-03-13","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":"2408.12102","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","created":"2024-08-22","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":"2509.26177","title":"Benchmarking Diarization Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2109.01164","title":"Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Development","created":"2021-09-01","cited_by_count":1,"area":null},{"id":"2209.11896","title":"Unsupervised active speaker detection in media content using cross-modal information","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2302.09523","title":"Probabilistic Back-ends for Online Speaker Recognition and Clustering","created":"2023-02-19","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":"2407.04293","title":"Systematic Evaluation of Online Speaker Diarization Systems Regarding their Latency","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2408.02341","title":"An approach to optimize inference of the DIART speaker diarization pipeline","created":"2024-08-05","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":"2601.19946","title":"MK-SGC-SC: Multiple Kernel Guided Sparse Graph Construction in Spectral Clustering for Unsupervised Speaker Diarization","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2607.23808","title":"Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2110.03380","title":"Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2207.12504","title":"Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free","created":"2022-07-25","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":"2406.09290","title":"Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speech","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2406.14464","title":"A Review of Common Online Speaker Diarization Methods","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2411.13674","title":"FabuLight-ASD: Unveiling Speech Activity via Body Language","created":"2024-11-20","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":"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":"2506.14750","title":"Exploring Speaker Diarization with Mixture of Experts","created":"2025-06-17","cited_by_count":0,"area":"moe"},{"id":"2603.16966","title":"CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization","created":"2026-03-17","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":"2604.13348","title":"Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.16568","title":"Fast When, Careful Who: Dual-Process Multiparty Turn-Taking with Diffusion Augmentation","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.22369","title":"Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.02504","title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.17544","title":"X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.28609","title":"Parametric Multimodal User Memory: Storing What Captions Cannot Carry","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2609.18521","title":"VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20833","title":"Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.02941","title":"FASTDIAR: Frame-level speaker encoder for Streaming Diarization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.20172","title":"MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20327","title":"Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}