# MSV Challenge 2022: NPU-HC Speaker Verification System for Low-resource Indian Languages

arXiv: https://arxiv.org/abs/2211.16694 · HTML: https://mlsanity.com/paper/2211.16694/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models.
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [CN-CELEB: a challenging Chinese speaker recognition dataset](https://mlsanity.com/paper/1911.01799/) (2019)
- [Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020](https://mlsanity.com/paper/2009.14153/) (2020)
- [The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification](https://mlsanity.com/paper/2010.11255/) (2020)
- [The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA](https://mlsanity.com/paper/1812.10260/) (2018)
- [Speaker verification using end-to-end adversarial language adaptation](https://mlsanity.com/paper/1811.02331/) (2018)
- [Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021](https://mlsanity.com/paper/2109.03568/) (2021)
- [Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification](https://mlsanity.com/paper/2106.09320/) (2021)
- [Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning](https://mlsanity.com/paper/2110.06565/) (2021)
- [NPU Speaker Verification System for INTERSPEECH 2020 Far-Field Speaker Verification Challenge](https://mlsanity.com/paper/2008.03521/) (2020)
- [Domain Agnostic Few-shot Learning for Speaker Verification](https://mlsanity.com/paper/2206.13700/) (2022)

## Abstract (arXiv)

This report describes the NPU-HC speaker verification system submitted to the O-COCOSDA Multi-lingual Speaker Verification (MSV) Challenge 2022, which focuses on developing speaker verification systems for low-resource Asian languages. We participate in the I-MSV track, which aims to develop speaker verification systems for various Indian languages. In this challenge, we first explore different neural network frameworks for low-resource speaker verification. Then we leverage vanilla fine-tuning and weight transfer fine-tuning to transfer the out-domain pre-trained models to the in-domain Indian dataset. Specifically, the weight transfer fine-tuning aims to constrain the distance of the weights between the pre-trained model and the fine-tuned model, which takes advantage of the previously acquired discriminative ability from the large-scale out-domain datasets and avoids catastrophic forgetting and overfitting at the same time. Finally, score fusion is adopted to further improve performance. Together with the above contributions, we obtain 0.223% EER on the public evaluation set, ranking 2nd place on the leaderboard. On the private evaluation set, the EER of our submitted system is 2.123% and 0.630% for the constrained and unconstrained sub-tasks of the I-MSV track, leading to the 1st and 3rd place in the ranking, respectively.