# Speaker recognition and diarization

Area: [Speech and audio language models](https://mlsanity.com/speech/index.md). HTML: https://mlsanity.com/speech/speaker-recognition-and-diarization/

## Key facts

- Speaker recognition and diarization: 832 papers on arXiv since 2021 (data through 19 Oct 2026).
- 131 of its 832 mapped papers (16%) cite “A Review of Speaker Diarization: Recent Advances with Deep Learning” (2021, arXiv 2101.09624).
- 97 of its 832 mapped papers (12%) cite “M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge” (2021, arXiv 2110.07393).
- 11 new papers 2 Oct–19 Oct.

## Most cited here

- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021), cited by 131 papers here
- [M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge](https://mlsanity.com/paper/2110.07393/) (2021), cited by 97 papers here
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022), cited by 60 papers here
- [MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification](https://mlsanity.com/paper/2203.15249/) (2022), cited by 51 papers here
- [CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking](https://mlsanity.com/paper/2303.00332/) (2023), cited by 50 papers here
- [Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech](https://mlsanity.com/paper/2105.09040/) (2021), cited by 47 papers here
- [Powerset multi-class cross entropy loss for neural speaker diarization](https://mlsanity.com/paper/2310.13025/) (2023), cited by 43 papers here
- [Streaming Multi-Talker ASR with Token-Level Serialized Output Training](https://mlsanity.com/paper/2202.00842/) (2022), cited by 42 papers here
- [End-to-End Speaker-Attributed ASR with Transformer](https://mlsanity.com/paper/2104.02128/) (2021), cited by 40 papers here
- [Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification](https://mlsanity.com/paper/2110.05777/) (2021), cited by 37 papers here

## New (2 Oct–19 Oct)

- [Manifold-Constrained Residual Adaptation with Frame-Adaptive Layer Aggregation for Speaker Verification](https://mlsanity.com/paper/2610.25892/) (2026-10-19)
- [MS-Bench: A Condition-Stratified Multi-Speaker ASR Benchmark](https://mlsanity.com/paper/2610.25824/) (2026-10-19)
- [Learning Speaker-Activity-Conditioned WavLM Speaker Embeddings with Real Conversational Data](https://mlsanity.com/paper/2610.25183/) (2026-10-18)
- [Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages](https://mlsanity.com/paper/2610.20327/) (2026-10-14)
- [Unsupervised Cross-device Speaker Diarization And Linking Through Spatiotemporal Structure](https://mlsanity.com/paper/2610.15978/) (2026-10-11)
- [OpenSVBench: Diagnosing Speaker Verification Generalization Across Deployment Scenarios](https://mlsanity.com/paper/2610.13760/) (2026-10-09)
- [Toward accurate speaker inventories for online speaker diarization](https://mlsanity.com/paper/2610.11278/) (2026-10-08)
- [Cross-Lingual Speaker Verification with Self-Supervised Pre-Trained Models](https://mlsanity.com/paper/2610.11099/) (2026-10-08)
- [Revisiting Label-Free Speaker Embedding Enhancement with vMF Profile Likelihood](https://mlsanity.com/paper/2610.06691/) (2026-10-05)
- [SepRQ : Self-Supervised Speech Mixture Representation Learning via Mask-Free, Multi-Scale Source Separation](https://mlsanity.com/paper/2610.04690/) (2026-10-03)
- [FASTDIAR: Frame-level speaker encoder for Streaming Diarization](https://mlsanity.com/paper/2610.02941/) (2026-10-02)