Third International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 2003)

Florence, Italy
December 10-12, 2003

Hoarse Voice Denoising for Real-Time DSP Implementation: Continuous Speech Assessment

Ernesto Iadanza, F. Dori, Claudia Manfredi, S. Dubini

Department of Electronics and Telecommunications, Università degli Studi di Firenze, Firenze, Italy

Voice hoarseness is mainly related to airflow turbulence in the vocal tract. It can be due to vocal fold paralysis, polyps, cordectomisation or other dysfunction, which alter regular speech production, and is commonly treated as a noise component in the speech signal. A denoising approach is proposed, based on low-order singular value decomposition (SVD) of matrices whose entries come from sampled speech data frames, properly organised. A prototype DSP board implementing the procedure was developed. Objective quality indexes are proposed, showing the results achieved with the proposed method both on vowel and consonantal sentences.

Index Terms. SVD, hoarse voice, DSP, continuous speech, real-time

Full Paper (reprinted with permission from Firenze University Press)

Bibliographic reference.  Iadanza, Ernesto / Dori, F. / Manfredi, Claudia / Dubini, S. (2003): "Hoarse voice denoising for real-time DSP implementation: continuous speech assessment", In MAVEBA-2003, 69-72.