Neural Domain Alignment For Spoken Language Recognition Based On Optimal Transport

Abstract

Domain shift poses a significant challenge in cross-domain spoken language recognition (SLR) by reducing its effectiveness. Unsupervised domain adaptation (UDA) algorithms have been explored to address domain shifts in SLR without relying on class labels in the target domain. One successful UDA approach focuses on learning domain-invariant representations to align feature distributions between domains. However, disregarding the class structure during the learning process of domain-invariant representations can result in over-alignment, negatively impacting the classification task. To overcome this limitation, we propose an optimal transport (OT)-based UDA algorithm for a cross-domain SLR, leveraging the distribution geometry structure-aware property of OT. An OT-based discrepancy measure on a joint distribution over feature and label information is considered during domain alignment in OT-based UDA. Our previous study discovered that completely aligning the distributions between the so

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylu2023neural

Related papers

• Unsupervised Neural Adaptation Model Based On Optimal Transport For Spoken Language Identification (2020)8.82
• Channel Adaptation For Speaker Verification Using Optimal Transport With Pseudo Label (2024)0.00
• Unsupervised Noise Adaptive Speech Enhancement By Discriminator-constrained Optimal Transport (2021)0.00
• Optimal Transport-based Adaptation In Dysarthric Speech Tasks (2021)0.00
• Boosting Cross-domain Speech Recognition With Self-supervision (2022)0.00
• Interpretable Dysarthric Speaker Adaptation Based On Optimal-transport (2022)2.26
• Cross-domain Adaptation Of Spoken Language Identification For Related Languages: The Curious Case Of Slavic Languages (2020)8.35
• MADI: Inter-domain Matching And Intra-domain Discrimination For Cross-domain Speech Recognition (2023)7.50