Salvato in:
Dettagli Bibliografici
Autori principali: Pohlhausen, Jule, Nespoli, Francesco, Bitzer, Joerg
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.00382
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912872342224896
author Pohlhausen, Jule
Nespoli, Francesco
Bitzer, Joerg
author_facet Pohlhausen, Jule
Nespoli, Francesco
Bitzer, Joerg
contents Recordings in everyday life require privacy preservation of the speech content and speaker identity. This contribution explores the influence of noise and reverberation on the trade-off between privacy and utility for low-cost privacy-preserving methods feasible for edge computing. These methods compromise spectral and temporal smoothing, speaker anonymization using the McAdams coefficient, sampling with a very low sampling rate, and combinations. Privacy is assessed by automatic speech and speaker recognition, while our utility considers voice activity detection and speaker diarization. Overall, our evaluation shows that additional noise degrades the performance of all models more than reverberation. This degradation corresponds to enhanced speech privacy, while utility is less deteriorated for some methods.
format Preprint
id arxiv_https___arxiv_org_abs_2408_00382
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Long-Term Conversation Analysis: Privacy-Utility Trade-off under Noise and Reverberation
Pohlhausen, Jule
Nespoli, Francesco
Bitzer, Joerg
Audio and Speech Processing
Recordings in everyday life require privacy preservation of the speech content and speaker identity. This contribution explores the influence of noise and reverberation on the trade-off between privacy and utility for low-cost privacy-preserving methods feasible for edge computing. These methods compromise spectral and temporal smoothing, speaker anonymization using the McAdams coefficient, sampling with a very low sampling rate, and combinations. Privacy is assessed by automatic speech and speaker recognition, while our utility considers voice activity detection and speaker diarization. Overall, our evaluation shows that additional noise degrades the performance of all models more than reverberation. This degradation corresponds to enhanced speech privacy, while utility is less deteriorated for some methods.
title Long-Term Conversation Analysis: Privacy-Utility Trade-off under Noise and Reverberation
topic Audio and Speech Processing
url https://arxiv.org/abs/2408.00382