Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386156720> ?p ?o ?g. }
- W4386156720 abstract "<sec> <title>UNSTRUCTURED</title> Large, curated datasets are required to leverage speech-based tools in healthcare. These are costly to produce, resulting in increased interest in data sharing. As speech can potentially identify speakers (i.e., voiceprints), sharing recordings raises privacy concerns. We examine the re-identification risk for speech recordings, without reference to demographic or metadata, using a state-of-the-art speaker identification model. We demonstrate that the risk is inversely related to the number of comparisons an adversary must consider, i.e., the ‘search space’. Risk is high for a small search space but drops as the search space grows (precision > 0.85 for < 1∗10^6 comparisons, precision < 0.5 for > 3∗10^6 comparisons). Next, we show that the nature of a speech recording influences re-identification risk, with non-connected speech (e.g., vowel prolongation) being harder to identify. Our findings suggest that speaker identification models can be used to re-identify participants in specific circumstances, but in practice, the re-identification risk appears small. </sec>" @default.
- W4386156720 created "2023-08-26" @default.
- W4386156720 creator A5005285557 @default.
- W4386156720 creator A5017176841 @default.
- W4386156720 creator A5031615915 @default.
- W4386156720 creator A5036223666 @default.
- W4386156720 creator A5046855704 @default.
- W4386156720 creator A5064456190 @default.
- W4386156720 creator A5090647314 @default.
- W4386156720 date "2023-08-21" @default.
- W4386156720 modified "2023-09-26" @default.
- W4386156720 title "Risk of re-identification for shared clinical speech recordings (Preprint)" @default.
- W4386156720 cites W1432028318 @default.
- W4386156720 cites W1481604723 @default.
- W4386156720 cites W1972756559 @default.
- W4386156720 cites W1977958021 @default.
- W4386156720 cites W2000428399 @default.
- W4386156720 cites W2041377702 @default.
- W4386156720 cites W2042750648 @default.
- W4386156720 cites W2098161667 @default.
- W4386156720 cites W2099592842 @default.
- W4386156720 cites W2112582577 @default.
- W4386156720 cites W2121812409 @default.
- W4386156720 cites W2137373451 @default.
- W4386156720 cites W2146875405 @default.
- W4386156720 cites W2154278880 @default.
- W4386156720 cites W2159999556 @default.
- W4386156720 cites W2170383904 @default.
- W4386156720 cites W2466455802 @default.
- W4386156720 cites W2608887242 @default.
- W4386156720 cites W2726515241 @default.
- W4386156720 cites W2754967293 @default.
- W4386156720 cites W2771385958 @default.
- W4386156720 cites W2790857402 @default.
- W4386156720 cites W2808631503 @default.
- W4386156720 cites W2889093877 @default.
- W4386156720 cites W2911160483 @default.
- W4386156720 cites W2953740025 @default.
- W4386156720 cites W2963693643 @default.
- W4386156720 cites W2968647719 @default.
- W4386156720 cites W2981087920 @default.
- W4386156720 cites W2995584712 @default.
- W4386156720 cites W2996636445 @default.
- W4386156720 cites W3022135431 @default.
- W4386156720 cites W3024144824 @default.
- W4386156720 cites W3024869864 @default.
- W4386156720 cites W3028563376 @default.
- W4386156720 cites W3033511014 @default.
- W4386156720 cites W3086590218 @default.
- W4386156720 cites W3095385778 @default.
- W4386156720 cites W3099081599 @default.
- W4386156720 cites W3103977047 @default.
- W4386156720 cites W3121150787 @default.
- W4386156720 cites W3124813086 @default.
- W4386156720 cites W3156027765 @default.
- W4386156720 cites W3161453586 @default.
- W4386156720 cites W3197646400 @default.
- W4386156720 cites W3199044515 @default.
- W4386156720 cites W3213403910 @default.
- W4386156720 cites W3216741049 @default.
- W4386156720 cites W4220886381 @default.
- W4386156720 cites W4223524567 @default.
- W4386156720 cites W4233400898 @default.
- W4386156720 cites W4237883802 @default.
- W4386156720 cites W4240777806 @default.
- W4386156720 cites W4245885592 @default.
- W4386156720 cites W4297841645 @default.
- W4386156720 cites W4385769280 @default.
- W4386156720 doi "https://doi.org/10.2196/preprints.52054" @default.
- W4386156720 hasPublicationYear "2023" @default.
- W4386156720 type Work @default.
- W4386156720 citedByCount "0" @default.
- W4386156720 crossrefType "posted-content" @default.
- W4386156720 hasAuthorship W4386156720A5005285557 @default.
- W4386156720 hasAuthorship W4386156720A5017176841 @default.
- W4386156720 hasAuthorship W4386156720A5031615915 @default.
- W4386156720 hasAuthorship W4386156720A5036223666 @default.
- W4386156720 hasAuthorship W4386156720A5046855704 @default.
- W4386156720 hasAuthorship W4386156720A5064456190 @default.
- W4386156720 hasAuthorship W4386156720A5090647314 @default.
- W4386156720 hasConcept C111919701 @default.
- W4386156720 hasConcept C116834253 @default.
- W4386156720 hasConcept C136764020 @default.
- W4386156720 hasConcept C153083717 @default.
- W4386156720 hasConcept C154945302 @default.
- W4386156720 hasConcept C2776214188 @default.
- W4386156720 hasConcept C2778572836 @default.
- W4386156720 hasConcept C2779581591 @default.
- W4386156720 hasConcept C28490314 @default.
- W4386156720 hasConcept C41008148 @default.
- W4386156720 hasConcept C43169469 @default.
- W4386156720 hasConcept C59822182 @default.
- W4386156720 hasConcept C86803240 @default.
- W4386156720 hasConcept C93518851 @default.
- W4386156720 hasConceptScore W4386156720C111919701 @default.
- W4386156720 hasConceptScore W4386156720C116834253 @default.
- W4386156720 hasConceptScore W4386156720C136764020 @default.
- W4386156720 hasConceptScore W4386156720C153083717 @default.
- W4386156720 hasConceptScore W4386156720C154945302 @default.
- W4386156720 hasConceptScore W4386156720C2776214188 @default.