{"total":22,"rows":[{"id":"2504.14183","title":"The First VoicePrivacy Attacker Challenge","created":"2025-04-19","cited_by_count":4,"area":null},{"id":"2505.13971","title":"The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2408.14229","title":"Holistic Uncertainty Estimation For Open-Set Recognition","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2505.14351","title":"FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for \\\"U-Tsang, Amdo and Kham Speech Dataset Generation","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2603.02781","title":"Scores Know Bobs Voice: Speaker Impersonation Attack","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2410.07428","title":"The First VoicePrivacy Attacker Challenge Evaluation Plan","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2508.19210","title":"Interpolating Speaker Identities in Embedding Space for Data Expansion","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.17662","title":"DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Model","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2603.24432","title":"What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2603.24569","title":"POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2606.06211","title":"FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.29335","title":"AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2509.03256","title":"Comparison of End-to-end Speech Assessment Models for the NOCASA 2025 Challenge","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2512.14961","title":"Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.10829","title":"Self-Supervised Learning for Speaker Recognition: A study and review","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.08560","title":"Uncertainty Estimation for the Open-Set Text Classification systems","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.17416","title":"L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.13669","title":"Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.22923","title":"Simple Language Normalization Wins: Cross-Lingual Speaker Verification for the TidyVoice 2026 Challenge","created":"2026-07-24","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":"2609.35043","title":"Mixed-Prior Decision Risk for Open-Set Recognition","created":"2026-09-28","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}],"next_cursor":null}