| Whispering is a common type of speech which is not often studied in speech technology. Perceptual and physiological studies show us that whispered speech is subtly different from phonated speech, and is surprisingly able to carry a tremendous amount of information. In this dissertation we consider the question: What makes whispering a good form of communication? We examine the differences between normal phonated speech and whispered speech, and gauge the effectiveness of state-of-the-art speech recognition algorithms at recognizing whisper. Our perceptual experiments add to the literature on the intelligibility of whispered speech. Comparisons with ASR results yield interesting insights into the differences between the two systems.;A method for building speech recognizers for whispered speech using limited whispered speech data is proposed and evaluated. Our approach effectively performs speaker-adaptation for whispered speech acoustic models without needing whispered speech from the target speaker. Results show improvement over the standard speaker-independent models. Our work opens up additional avenues for research, which are outlined in the conclusions. |
