@inproceedings{2624cae27f0848e5858917d1fdf8d2a7,
title = "Frequency-domain delexicalization using surrogate vowels",
abstract = "We propose a delexicalization algorithm that renders the lexical content of an utterance unintelligible, while preserving important acoustic prosodic cues, as well as naturalness and speaker identity. This is achieved by replacing voiced regions by spectral slices from a surrogate vowel, and by averaging the magnitude spectrum during unvoiced regions. Perceptual tests were carried out comparing sentences that were either unprocessed or delexicalized, using a baseline or the proposed method. An intelligibility test resulted in a keyword recall rate of 92% for the unprocessed sentences, and near complete unintelligibility for both delexicalization methods. Affect recognition was at 65% for unprocessed sentences, and 46% and 49% for the baseline and the proposed method, respectively. Preference tests showed that the proposed method preserved drastically more speaker identity, and sounded more natural than the baseline.",
keywords = "Affect, Delexicalization, Intelligibility",
author = "Alexander Kain and {Van Santen}, Jan",
note = "Funding Information: This research was supported by grants from the National Institute on Deafness and Other Communication Disorders, 1R21DC010239 (Lois Black, PI) and from the National Science Foundation, 0905095 (Jan van Santen, PI). The views herein are those of the authors and do not reflect the views of the funding agencies.",
year = "2010",
language = "English (US)",
series = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",
publisher = "International Speech Communication Association",
pages = "474--477",
booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",
}