Detecting Spoof Voices in Asian Non-Native Speech: An Indonesian and Thai Case Study

TL;DR

This paper develops spoofing detection systems for non-native Indonesian and Thai speech, highlighting the challenges and benefits of including non-native data to improve detection accuracy in diverse linguistic contexts.

Contribution

Introduces a dataset and machine learning-based spoofing detection methods tailored for non-native speech, emphasizing the importance of non-native data in training.

Findings

Native CM struggles with non-native speech

Incorporating non-native data improves detection performance

Proposed features and classifiers enhance spoofing detection

Abstract

This study focuses on building effective spoofing countermeasures (CMs) for non-native speech, specifically targeting Indonesian and Thai speakers. We constructed a dataset comprising both native and non-native speech to facilitate our research. Three key features (MFCC, LFCC, and CQCC) were extracted from the speech data, and three classic machine learning-based classifiers (CatBoost, XGBoost, and GMM) were employed to develop robust spoofing detection systems using the native and combined (native and non-native) speech data. This resulted in two types of CMs: Native and Combined. The performance of these CMs was evaluated on both native and non-native speech datasets. Our findings reveal significant challenges faced by Native CM in handling non-native speech, highlighting the necessity for domain-specific solutions. The proposed method shows improved detection capabilities, demonstrating the importance of incorporating non-native speech data into the training process. This work lays the foundation for more effective spoofing detection systems in diverse linguistic contexts.