Weakly Supervised PLDA Training

Abstract

PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labelled development data, which is highly expensive in most cases. We present a cheap PLDA training approach, which assumes that speakers in the same session can be easily separated, and speakers in different sessions are simply different. This results in `weak labels' which are not fully accurate but cheap, leading to a weak PLDA training. Our experimental results on real-life large-scale telephony customer service achieves demonstrated that the weak training can offer good performance when human-labelled data are limited. More interestingly, the weak training can be employed as a discriminative adaptation approach, which is more efficient than the prevailing unsupervised method when human-labelled data are insufficient.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2016weakly

Related papers

• Local Training For PLDA In Speaker Verification (2016)0.00
• Multiobjective Optimization Training Of PLDA For Speaker Verification (2018)2.26
• Blind Score Normalization Method For PLDA Based Speaker Recognition (2016)0.00
• A Generalized Framework For Domain Adaptation Of PLDA In Speaker Recognition (2020)7.50
• Domain Adaptation Based Speaker Recognition On Short Utterances (2016)0.00
• End-to-end DNN Based Speaker Recognition Inspired By I-vector And PLDA (2017)10.35
• A Discriminative Hierarchical Plda-based Model For Spoken Language Recognition (2022)5.24
• Improving Short Utterance PLDA Speaker Verification Using SUV Modelling And Utterance Partitioning Approach (2016)0.00