PITCH EXTRACTION AND VOICED UNVOICED DETECTION OF SPEECH BY CROSS-COUPLING MULTILAYERED NEURAL-NETWORK WITH FEEDBACK ARCHITECTURE/

Pitch frequency is one of the most important voice characteristics, an d its accurate extraction is important not only in speech analysis and synthesis, but also in speech coding, speech recognition, speaker rec ognition, and the like. Existing methods of improving extraction accur acy include waveform processing, correlative processing, and spectral processing. This paper describes the use of a neural network to extrac t pitch from voice features delivered from the bandpass filter pairs ( BPFPs) proposed by Fonda et al. Three types of multi-layered neutral n etworks able to learn time-continuity and high accuracy discrimination functions and have st recurrent structure are tested. The cross-coupl ing multi-layered neural network with feedback architecture gives the best improvement over conventional neural networks, and exhibits super ior ability for learning time continuity of pitch and UN information. (C) 1997 Scripta Technica, Inc.