{"total":38,"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":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"area":null},{"id":"2110.03151","title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR","created":"2021-10-07","cited_by_count":22,"area":null},{"id":"2107.01545","title":"Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2021-07-04","cited_by_count":15,"area":null},{"id":"2110.05781","title":"BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications","created":"2021-10-12","cited_by_count":13,"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":"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":"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":"2105.02096","title":"End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings","created":"2021-05-05","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":"2104.02879","title":"Adapting Speaker Embeddings for Speaker Diarisation","created":"2021-04-07","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":"2202.13826","title":"Magnitude-aware Probabilistic Speaker Embeddings","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2208.08042","title":"The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines","created":"2022-08-17","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":"2406.07816","title":"Spoof Diarization: \"What Spoofed When\" in Partially Spoofed Audio","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2109.01537","title":"A Longitudinal Multi-modal Dataset for Dementia Monitoring and Diagnosis","created":"2021-09-03","cited_by_count":2,"area":null},{"id":"2203.09767","title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","created":"2022-03-18","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":"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":"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":"2111.13694","title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2112.05555","title":"Shennong: a Python toolbox for audio speech features extraction","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2211.00549","title":"No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable acceleration","created":"2022-11-01","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":"2305.01155","title":"Lessons Learned in ATCO2: 5000 hours of Air Traffic Control Communications for Robust Automatic Speech Recognition and Understanding","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2311.03021","title":"Detecting agreement in multi-party dialogue: evaluating speaker diarisation versus a procedural baseline to enhance user engagement","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2404.17552","title":"A Semi-Automatic Approach to Create Large Gender- and Age-Balanced Speaker Corpora: Usefulness of Speaker Diarization & Identification","created":"2024-04-26","cited_by_count":1,"area":null},{"id":"2104.02469","title":"Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2107.00636","title":"ESPnet-ST IWSLT 2021 Offline Speech Translation System","created":"2021-07-01","cited_by_count":0,"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":"2203.16646","title":"Generation of Speaker Representations Using Heterogeneous Training Batch Assembly","created":"2022-03-30","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":"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":"2607.18704","title":"What the Waveform Knows: Transparent-first Speech and Audio Intelligence with Caption Studio","created":"2026-07-21","cited_by_count":0,"area":null}],"next_cursor":null}