# Distance-based Weight Transfer from Near-field to Far-field Speaker Verification

arXiv: https://arxiv.org/abs/2303.00264 · HTML: https://mlsanity.com/paper/2303.00264/

## Key facts

- Cited by 1 papers 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 15 of its 29 references that are in the map.
- First posted on arXiv 1 Mar 2023.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [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)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning](https://mlsanity.com/paper/2004.11627/) (2020)
- [The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA](https://mlsanity.com/paper/1812.10260/) (2018)
- [HI-MIA : A Far-field Text-Dependent Speaker Verification Database and the Baselines](https://mlsanity.com/paper/1912.01231/) (2019)
- [Speaker verification using end-to-end adversarial language adaptation](https://mlsanity.com/paper/1811.02331/) (2018)
- [Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning](https://mlsanity.com/paper/1901.02348/) (2019)
- [The FFSVC 2020 Evaluation Plan](https://mlsanity.com/paper/2002.00387/) (2020)
- [NPU Speaker Verification System for INTERSPEECH 2020 Far-Field Speaker Verification Challenge](https://mlsanity.com/paper/2008.03521/) (2020)
- [Length- and Noise-aware Training Techniques for Short-utterance Speaker Recognition](https://mlsanity.com/paper/2008.12218/) (2020)
- [MultiSV: Dataset for Far-Field Multi-Channel Speaker Verification](https://mlsanity.com/paper/2111.06458/) (2021)

## Built on by (most cited first, 1 of 1)

- [Whisper-SV: Adapting Whisper for Low-data-resource Speaker Verification](https://mlsanity.com/paper/2407.10048/) (2024)

## Abstract (arXiv)

The scarcity of labeled far-field speech is a constraint for training superior far-field speaker verification systems. Fine-tuning the model pre-trained on large-scale near-field speech substantially outperforms training from scratch. However, the fine-tuning method suffers from two limitations--catastrophic forgetting and overfitting. In this paper, we propose a weight transfer regularization(WTR) loss to constrain the distance of the weights between the pre-trained model with large-scale near-field speech and the fine-tuned model through a small number of far-field speech. With the WTR loss, the fine-tuning process takes advantage of the previously acquired discriminative ability from the large-scale near-field speech without catastrophic forgetting. Meanwhile, we use the PAC-Bayes generalization theory to analyze the generalization bound of the fine-tuned model with the WTR loss. The analysis result indicates that the WTR term makes the fine-tuned model have a tighter generalization upper bound. Moreover, we explore three kinds of norm distance for weight transfer, which are L1-norm distance, L2-norm distance and Max-norm distance. Finally, we evaluate the effectiveness of the WTR loss on VoxCeleb (pre-trained dataset) and FFSVC (fine-tuned dataset) datasets.