Abstract
This paper presents the results of an experimental research of recognition of whispered speech, as a specific form of verbal communication, based on application of artificial neural networks (ANN). The paper also describes the speech database of words that were spoken in whispered and normal manner, which was especially created for this study. Part of this database was used for preliminary training and testing the ANN. The case of the speaker dependent recognition was tested, and the results showed 100% accuracy in the case of speech recognition and 99,3% in the case of whisper recognition. In the case of whisper recognition, when ANN was trained for the normal speech the score of whisper recognition was 59%, and vice versa, when the ANN was trained with whisper the speech recognition was 66.4%.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
