Impact of pathological speech on speaker anonymization

  • With the ever-increasing usage of voice assistants, concerns for privacy and data security arise. Speech contains highly personal data that can be exploited for user profiling or identification [1]. On-device speech anonymization can serve as a measure to counteract this [2]. While these anonymization systems are being tested and evaluated through challenges and benchmarks [3], the commonly used datasets include no or only a few individuals with speech impairments, leading to low inclusivity, possible data bias, and privacy concerns for these groups [5]. For anonymization to work, it is crucial to evaluate and counteract bias if needed. Stuttering is a speech disorder with diverse characteristics. The well-known, defining symptoms are blocks, repetition and prolongation of sounds, syllables, and words while speaking [4]. The different primary stuttering symptoms vary strongly in their characteristics and occur over a different time context, making stuttering an ideal candidate to study the effects of pathological speech on theWith the ever-increasing usage of voice assistants, concerns for privacy and data security arise. Speech contains highly personal data that can be exploited for user profiling or identification [1]. On-device speech anonymization can serve as a measure to counteract this [2]. While these anonymization systems are being tested and evaluated through challenges and benchmarks [3], the commonly used datasets include no or only a few individuals with speech impairments, leading to low inclusivity, possible data bias, and privacy concerns for these groups [5]. For anonymization to work, it is crucial to evaluate and counteract bias if needed. Stuttering is a speech disorder with diverse characteristics. The well-known, defining symptoms are blocks, repetition and prolongation of sounds, syllables, and words while speaking [4]. The different primary stuttering symptoms vary strongly in their characteristics and occur over a different time context, making stuttering an ideal candidate to study the effects of pathological speech on the application of anonymization techniques. This paper analyzes the impact of stuttering on speaker anonymization, regarding the level of anonymity and utility. We present two methods to conceal speaker identity, us- ing voice conversion and re-synthesis. Firstly, Voice conversion, a process that adapts the way a source speaker speaks to a target speaker. It preserves some prosody of the source speaker, especially temporal aspects, with the goal of protecting the identity while at the same time preserving pathologic speech patterns. This could be applied in pathology-related processing, such as self-help training applications. Secondly, re-synthesis, based on an automatic speech recognition generating a transcript, which is afterward used to synthesize a new voice by a text-to-speech system. This process disentangles speaker information and text, granting a high level of anonymization. To compare these methods, we use subjective and objective measures.show moreshow less

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Jan Hintz, Sebastian P. BayerlORCiD, Yamini Sinha, Korbinian Riedhammer, Ingo Siegert
Subtitle (English):A Proof of Concept
Document Type:conference proceeding (article)
Language:English
Reviewed:Begutachtet/Reviewed
Release Date:2024/07/08
Pagenumber:4
Konferenzangabe:Fortschritte der Akustik - DAGA 2023
institutes:Fakultät Informatik
Licence (German):Keine Lizenz - Deutsches Urheberrecht gilt
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.