Unsupervised Neural Adaptation Model Based On Optimal Transport For Spoken Language Identification

Abstract

Due to the mismatch of statistical distributions of acoustic speech between training and testing sets, the performance of spoken language identification (SLID) could be drastically degraded. In this paper, we propose an unsupervised neural adaptation model to deal with the distribution mismatch problem for SLID. In our model, we explicitly formulate the adaptation as to reduce the distribution discrepancy on both feature and classifier for training and testing data sets. Moreover, inspired by the strong power of the optimal transport (OT) to measure distribution discrepancy, a Wasserstein distance metric is designed in the adaptation loss. By minimizing the classification loss on the training data set with the adaptation loss on both training and testing data sets, the statistical distribution difference between training and testing domains is reduced. We carried out SLID experiments on the oriental language recognition (OLR) challenge data corpus where the training and testing data se

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keylu2020unsupervised

Related papers

• Neural Domain Alignment For Spoken Language Recognition Based On Optimal Transport (2023)0.00
• Optimal Transport-based Adaptation In Dysarthric Speech Tasks (2021)0.00
• Unsupervised Noise Adaptive Speech Enhancement By Discriminator-constrained Optimal Transport (2021)0.00
• Interpretable Dysarthric Speaker Adaptation Based On Optimal-transport (2022)2.26
• Channel Adaptation For Speaker Verification Using Optimal Transport With Pseudo Label (2024)0.00
• Cross-domain Adaptation Of Spoken Language Identification For Related Languages: The Curious Case Of Slavic Languages (2020)8.35
• Unsupervised Domain Adaptation By Adversarial Learning For Robust Speech Recognition (2018)0.00
• Instance-based Model Adaptation For Direct Speech Translation (2019)0.00