mlsanityData to 19 Oct 2026

Language-Invariant Multilingual Speaker Verification for the TidyVoice 2026 Challenge

arXiv 2603.08092 ↗First posted 9 Mar 2026eess.AScited by 1

On the map: Speech and audio language models → Speaker recognition and diarization

Abstract (arXiv)

Multilingual speaker verification (SV) remains challenging due to limited cross-lingual data and language-dependent information in speaker embeddings. This paper presents a language-invariant multilingual SV system for the TidyVoice 2026 Challenge. We adopt the multilingual self-supervised w2v-BERT 2.0 model as the backbone, enhanced with Layer Adapters and Multi-scale Feature Aggregation to better exploit multi-layer representations. A language-adversarial training strategy with a Gradient Reversal Layer is applied to promote language-invariant speaker embeddings. Moreover, a multilingual zero-shot text-to-speech system is used to synthesize speech in multiple languages, improving language diversity. Experimental results demonstrate that fine-tuning the large-scale pretrained model yields competitive performance, while language-adversarial training further enhances robustness. In addition, synthetic speech augmentation provides additional gains under limited training data conditions. Source code is available at https://github.com/ZXHY-82/LI-MSV-TidyVoice2026.

Key facts. Cited by 1 paper in the map (data through 19 Oct 2026). Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models. Builds on 32 of its 37 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

32 of 37 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026TidyVoice 2026 Challenge Evaluation Plan29 Jan
  2. 2025Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning5 Oct
  3. 2024Reshape Dimensions Network for Speaker Recognition25 Jul
  4. 2024VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark16 Jul
  5. 2023Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation6 Sep
  6. 2023The DKU-MSXF Speaker Verification System for the VoxCeleb Speaker Recognition Challenge 202317 Aug
  7. 2023Exploring Binary Classification Loss For Speaker Verification17 Jul
  8. 2023CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking1 Mar
  9. 2022MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification29 Mar
  10. 2021Simple Attention Module based Speaker Verification with Iterative noisy label detection13 Oct

Other references · 22

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,833
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,661
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 4,385
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,762
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 2,135
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,949
  7. 2018VoxCeleb2: Deep Speaker Recognitioncited by 1,166
  8. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 980
  9. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 864
  10. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 694
  11. 2020Beyond English-Centric Multilingual Machine Translationcited by 566
  12. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 412
10 more
  1. 2023Seamless: Multilingual Expressive and Streaming Speech Translationcited by 235
  2. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 215
  3. 2018Attentive Statistics Pooling for Deep Speaker Embeddingcited by 207
  4. 2026Qwen3-TTS Technical Reportcited by 150
  5. 2019CN-CELEB: a challenging Chinese speaker recognition datasetcited by 123
  6. 2018Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition Systemcited by 79
  7. 2020The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verificationcited by 69
  8. 2020CN-Celeb: multi-genre speaker recognitioncited by 66
  9. 20233D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglementcited by 31
  10. 2022Cross-Age Speaker Verification: Learning Age-Invariant Speaker Embeddingscited by 12

Built on by

Cited by year (2026 to 19 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AMECxSV: Adaptive Metadata-Driven Embedding-Fusion Calibration for X-Lingual Speaker Verificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026TidyVoice: A Curated Multilingual Dataset for Speaker Verification Derived from Common Voice
  2. 2026Cross-Lingual Speaker Verification with Self-Supervised Pre-Trained Models
  3. 2025Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings
  4. 2021Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information
  5. 2026Simple Language Normalization Wins: Cross-Lingual Speaker Verification for the TidyVoice 2026 Challenge
  6. 2022Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information
  7. 2026L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification
  8. 2022Disentangled representation learning for multilingual speaker recognition