Speaker recognition and diarization

1. This week · 2
2. 19 OctManifold-Constrained Residual Adaptation with Frame-Adaptive Layer Aggregation for Speaker Verification
3. 19 OctMS-Bench: A Condition-Stratified Multi-Speaker ASR Benchmark also fits: ASR evaluation, bias and atypical speech
4. Earlier · 9
5. 18 OctLearning Speaker-Activity-Conditioned WavLM Speaker Embeddings with Real Conversational Data
6. 14 OctAnuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages
7. 11 OctUnsupervised Cross-device Speaker Diarization And Linking Through Spatiotemporal Structure
8. 9 OctOpenSVBench: Diagnosing Speaker Verification Generalization Across Deployment Scenarios also fits: Audio language models and spoken dialogue
9. 8 OctToward accurate speaker inventories for online speaker diarization
10. 8 OctCross-Lingual Speaker Verification with Self-Supervised Pre-Trained Models
11. 5 OctRevisiting Label-Free Speaker Embedding Enhancement with vMF Profile Likelihood
12. 3 OctSepRQ : Self-Supervised Speech Mixture Representation Learning via Mask-Free, Multi-Scale Source Separation

1. A Review of Speaker Diarization: Recent Advances with Deep Learning2021cited by 131 here
2. M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge2021cited by 97 here
3. Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit2022cited by 60 here
4. MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification2022cited by 51 here
5. CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking2023cited by 50 here

Each paper on the line cites the one before.

1. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 131 here
2. 2021Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphonecited by 25 here
3. 2022Streaming Multi-Talker ASR with Token-Level Serialized Output Trainingcited by 42 here
4. 2023The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarioscited by 35 here
5. 2024NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcriptioncited by 36 here
6. 2024Leveraging Self-Supervised Learning for Speaker Diarizationcited by 33 here

The 24 most cited of 1,053.

1. 6Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech202147
2. 7Powerset multi-class cross entropy loss for neural speaker diarization202343
3. 8Streaming Multi-Talker ASR with Token-Level Serialized Output Training202242
4. 9End-to-End Speaker-Attributed ASR with Transformer202140
5. 10Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification202137
6. 11NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription202436
7. 12Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR202136
8. 13The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios202335
9. 14Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification202134
10. 15Leveraging Self-Supervised Learning for Speaker Diarization202433