Optimization Of The Area Under The ROC Curve Using Neural Network Supervectors For Text-dependent Speaker Verification

Abstract

This paper explores two techniques to improve the performance of text-dependent speaker verification systems based on deep neural networks. Firstly, we propose a general alignment mechanism to keep the temporal structure of each phrase and obtain a supervector with the speaker and phrase information, since both are relevant for a text-dependent verification. As we show, it is possible to use different alignment techniques to replace the global average pooling providing significant gains in performance. Moreover, we also present a novel back-end approach to train a neural network for detection tasks by optimizing the Area Under the Curve (AUC) as an alternative to the usual triplet loss function, so the system is end-to-end, with a cost function close to our desired measure of performance. As we can see in the experimental section, this approach improves the system performance, since our triplet neural network based on an approximation of the AUC (aAUC) learns how to discriminate betwee

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keymingote2019optimization

Related papers

• Partial AUC Optimization Based Deep Speaker Embeddings With Class-center Learning For Text-independent Speaker Verification (2019)9.59
• Differentiable Supervector Extraction For Encoding Speaker And Phrase Information In Text Dependent Speaker Verification (2018)2.26
• Speaker Verification By Partial AUC Optimization With Mahalanobis Distance Metric Learning (2019)9.92
• Neural Network Based Speaker Classification And Verification Systems With Enhanced Features (2017)8.60
• P-vectors: A Parallel-coupled Tdnn/transformer Network For Speaker Verification (2023)5.84
• How To Leverage Dnn-based Speech Enhancement For Multi-channel Speaker Verification? (2022)0.00
• On Residual CNN In Text-dependent Speaker Verification Task (2017)7.16
• Neural Scoring: A Refreshed End-to-end Approach For Speaker Recognition In Complex Conditions (2024)0.00