Evaluating speech intelligibility enhancement for HMM-based synthetic speech in noise
Simon King, Junichi Yamagishi, Cassia Valentini-Botinhao · Edinburgh Research Explorer (University of Edinburgh) · 2012
It is possible to increase the intelligibility of speech in noise by enhancing the clean speech signal. In this pa- per we demonstrate the effects of modifying the spectral envelope of synthetic speech according to the environ- mental noise. To achieve this, we modify Mel cepstral coefficients according to an intelligibility measure that accounts for glimpses of speech in noise: the Glimpse Proportion measure. We evaluate this method against a baseline synthetic voice trained only with normal speech and a topline voice trained with Lombard speech, as well as natural speech. The intelligibility of these voices was measured when mixed with speech-shaped noise and with a competing speaker at three different levels. The Lom- bard voices, both natural and synthetic, were more intelli- gible than the normal voices in all conditions. For speech- shaped noise, the proposed modified voice was as intel- ligible as the Lombard synthetic voice without requiring any recordings of Lombard speech, which are hard to ob- tain. However, in the case of competing talker noise, the Lombard synthetic voice was more intelligible than the proposed modified voice.