Noise reduction in whisper speech based on the auditory masking model
2010 (English)Conference paper (Refereed) Published
This paper presents the issue of whispered speech enhancement. Based on multi-band spectral subtraction method where the introduced musical residual noise occurs, the proposed approach performs parametric subtraction according to the WSS (Whispered Sensitive Scale) method that is particular for whispered speech processing and auditory masking model. The algorithm is characterized by a tradeoff mechanism between the amount of the whispered speech distortion, noise reduction, and the level of musical residual noise, which are determined by appropriate adjusting the subtraction parameters. Compared with traditional subtractive-type algorithms, the proposed method results in a significant reduction of musical residual noise. Finally, objective and subjective evaluations are implemented illustrating the improvements over traditional subtractive-type algorithms.
Place, publisher, year, edition, pages
Kunming: IEEE , 2010.
auditory masking model, multiband spectral subtraction method, musical residual noise, noise reduction, parametric subtraction, speech distortion, whispered sensitive scale, whispered speech enhancement
Signal Processing Medical Laboratory and Measurements Technologies Computer Science
IdentifiersURN: urn:nbn:se:bth-6621DOI: 10.1109/ICINA.2010.5636688Local ID: oai:bth.se:forskinfoC27C16FE730E8C97C1257D55002B1F81ISBN: 978-1-4244-8104-0 OAI: oai:DiVA.org:bth-6621DiVA: diva2:834143
Information Networking and Automation (ICINA)