Multisensor input for a speech enhancement equipment: system architecture and experimental results
Livio Busnelli, N. Dal Degan, L. Vetrano · 1987
Speech enhancement techniques based on two inputs algorithms are completely inadequate if amoient noise reveals strong incoherenceo On the other hana, enhancement obtained by using spectral subtraction methods presents several inconveniences while also being rather complexo The herein presented equi~ment and the relevant algorithms use an array of input sensors to p~ck-up the speech in a no~sy environment; appro2riate signal processing permits to exploit both the spatial coherence of the s~eech and incoFierence of noiseo The signal to noise ratio of the output s~gnal shows a very good accordance with that of the theoretical modelo The processing load can be undertaken by currently available DSP technologyo