mlsanityData to 14 Oct 2026

Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit

arXiv 2210.17016 ↗First posted 31 Oct 2022cs.SD eess.AScited by 97

Not on the map. Why?

Abstract (arXiv)

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://github.com/wenet-e2e/wespeaker.

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Oct 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 24; 2025: 32; 2026: 34.

97 papers.

Sort:

By area:

  1. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 113
  2. 2024Autoregressive Diffusion Transformer for Text-to-Speech Synthesiscited by 34
  3. 2023RepCodec: A Speech Representation Codec for Speech Tokenizationcited by 27
  4. 2024MaskSR: Masked Language Model for Full-band Speech Restorationcited by 24
  5. 2025F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimizationcited by 24
  6. 2024ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf modelscited by 22
  7. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  8. 2024Coding Speech through Vocal Tract Kinematicscited by 18
  9. 2025FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matchingcited by 17
  10. 2024TTSDS -- Text-to-Speech Distribution Scorecited by 14
  11. 2023Disentangling Voice and Content with Self-Supervision for Speaker Recognitioncited by 13
  12. 2024What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysiscited by 11
38 more
  1. 2024TSELM: Target Speaker Extraction using Discrete Tokens and Language Modelscited by 10
  2. 2024TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touchcited by 10
  3. 2025Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Playcited by 10
  4. 2025Predicting Turn-Taking and Backchannel in Human-Machine Conversations Using Linguistic, Acoustic, and Visual Signalscited by 10
  5. 2023DDTSE: Discriminative Diffusion Model for Target Speech Extractioncited by 8
  6. 2025TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systemscited by 8
  7. 2025DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesiscited by 8
  8. 2024A Benchmark for Multi-speaker Anonymizationcited by 7
  9. 2024StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusioncited by 7
  10. 2024Certification of Speaker Recognition Models to Additive Perturbationscited by 6
  11. 2024The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environmentscited by 6
  12. 2025MeanFlowSE: one-step generative speech enhancement via conditional mean flowcited by 6
  13. 2025UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalitiescited by 6
  14. 2026A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilationcited by 6
  15. 2024Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibilitycited by 5
  16. 2024DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesiscited by 5
  17. 2025LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Modelscited by 5
  18. 2023Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verificationcited by 4
  19. 2024Mamba-based Segmentation Model for Speaker Diarizationcited by 4
  20. 2025The First VoicePrivacy Attacker Challengecited by 4
  21. 2025MeanFlow-TSE: One-Step Generative Target Speaker Extraction with Mean Flowcited by 4
  22. 2025SDBench: A Comprehensive Benchmark Suite for Speaker Diarizationcited by 3
  23. 2025Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruningcited by 3
  24. 2025Adaptive Deterministic Flow Matching for Target Speaker Extractioncited by 3
  25. 2024Robust Channel Learning for Large-Scale Radio Speaker Verificationcited by 2
  26. 2024Investigation of Speaker Representation for Target-Speaker Speech Processingcited by 2
  27. 2025Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesiscited by 2
  28. 2025LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Modelscited by 2
  29. 2025NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversioncited by 2
  30. 2026Scores Know Bobs Voice: Speaker Impersonation Attackcited by 2
  31. 2023Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversioncited by 1
  32. 2024Systematic Evaluation of Online Speaker Diarization Systems Regarding their Latencycited by 1
  33. 2024Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matchingcited by 1
  34. 2024Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillationcited by 1
  35. 2024The First VoicePrivacy Attacker Challenge Evaluation Plancited by 1
  36. 2025Comparative Evaluation of Expressive Japanese Character Text-to-Speech with VITS and Style-BERT-VITS2cited by 1
  37. 2025Interpolating Speaker Identities in Embedding Space for Data Expansioncited by 1
  38. 2025Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safetycited by 1

50 most cited of 97 All 97 (JSON)