Bayesian X-vector: Bayesian Neural Network Based X-vector System For Speaker Verification
2020 · Xu Li, Jinghua Zhong, Jianwei Yu, et al.
Abstract
Speaker verification systems usually suffer from the mismatch problem between training and evaluation data, such as speaker population mismatch, the channel and environment variations. In order to address this issue, it requires the system to have good generalization ability on unseen data. In this work, we incorporate Bayesian neural networks (BNNs) into the deep neural network (DNN) x-vector speaker verification system to improve the system's generalization ability. With the weight uncertainty modeling provided by BNNs, we expect the system could generalize better on the evaluation data and make verification decisions more accurately. Our experiment results indicate that the DNN x-vector system could benefit from BNNs especially when the mismatch problem is severe for evaluations using out-of-domain data. Specifically, results show that the system could benefit from BNNs by a relative EER decrease of 2.66% and 2.32% respectively for short- and long-utterance in-domain evaluations. Ad
Authors
(none)
Tags
Stats
Related papers
- Speechnas: Towards Better Trade-off Between Latency And Accuracy For Large-scale Speaker Verification (2021)9.76
- Multi-task Learning With High-order Statistics For X-vector Based Text-independent Speaker Verification (2019)8.35
- Deep Neural Network Based I-vector Mapping For Speaker Verification Using Short Utterances (2018)0.00
- An Improved Deep Neural Network For Modeling Speaker Characteristics At Different Temporal Scales (2020)6.34
- Generative X-vectors For Text-independent Speaker Verification (2018)7.16
- Gaussian-constrained Training For Speaker Verification (2018)8.35
- Gaussian Speaker Embedding Learning For Text-independent Speaker Verification (2020)0.00
- Bayesian HMM Clustering Of X-vector Sequences (vbx) In Speaker Diarization: Theory, Implementation And Analysis On Standard Tasks (2020)0.00