METHODS OF SPEECH SIGNAL SEGMENTATION FOR MULTIMODAL SPEECH RECOGNITION

Abstract

Segmentation of a speech signal is one of the most important tasks in the field of computer science and information systems for speech processing and recognition. Segmentation of the speech signal is necessary to isolate the characteristic features of the speaker’s voice in certain segments of the speech signal and restore the shape of the vocal tract based on an acoustic feature, which can be used in speech synthesis from the input text and speech recognition.