Improving Speaker De-identification With Functional Data Analysis Of F0 Trajectories

Abstract

Due to a constantly increasing amount of speech data that is stored in different types of databases, voice privacy has become a major concern. To respond to such concern, speech researchers have developed various methods for speaker de-identification. The state-of-the-art solutions utilize deep learning solutions which can be effective but might be unavailable or impractical to apply for, for example, under-resourced languages. Formant modification is a simpler, yet effective method for speaker de-identification which requires no training data. Still, remaining intonational patterns in formant-anonymized speech may contain speaker-dependent cues. This study introduces a novel speaker de-identification method, which, in addition to simple formant shifts, manipulates f0 trajectories based on functional data analysis. The proposed speaker de-identification method will conceal plausibly identifying pitch characteristics in a phonetically controllable manner and improve formant-based speake

Stats

• citations27
• S2 citations—
• github stars0
• HF likes0
• heat score10.85
• arxiv keytavi2022improving

Related papers

• Exploring The Importance Of F0 Trajectories For Speaker Anonymization Using X-vectors And Neural Waveform Models (2021)0.00
• Voiceprivacy 2022 System Description: Speaker Anonymization With Feature-matched F0 Trajectories (2022)0.00
• A Study Of F0 Modification For X-vector Based Speech Pseudonymization Across Gender (2021)0.00
• Privacy-utility Balanced Voice De-identification Using Adversarial Examples (2022)0.00
• Speaker De-identification System Using Autoencoders And Adversarial Training (2020)0.00
• Traditional Machine Learning For Pitch Detection (2019)10.85
• DEEPF0: End-to-end Fundamental Frequency Estimation For Music And Speech Signals (2021)10.35
• Waveform To Single Sinusoid Regression To Estimate The F0 Contour From Noisy Speech Using Recurrent Deep Neural Networks (2018)6.77