This paper concerns the problem of enhancing voice quality for people suffering from dysphonia, caused by airflow turbulence in the vocal tract, for irregular vocal folds vibration. A generalized subspace approach is proposed for enhancement of speech corrupted by additive noise, regardless of whether it is white or not. The clean signal is estimated by nulling the signal components in the noise subspace and retaining the components in the signal subspace. Two approaches are compared, taking into account both signal and noise, or signal only, eigenvalues. An optimised adaptive comb filter is applied first, to reduce noise between harmonics. Objective voice quality measures demonstrate improvements in voice quality when tested with sustained vowels or words corrupted with “hoarseness noise”. The intention is to provide users (disabled people, as well as clinicians) with a device allowing intelligible and effortless speech for dysphonics, and useful information concerning possible functional recovering. This will be of use to people in social situations where they interact with non-familiar communication partners, such as at work, and in everyday life.

Index Terms. hoarseness, voice denoising, GSVD, comb filtering, voice quality, pitch, noise, formants.