Arithmetic Research Of Voice Conversion

Speech signal is one of the most important methods for people to get and utilize information. Speech signal processing is a new cross-subject that process speech signal using digital signal processing technology, and it is a all-around application based on many subjects. Voice conversion, as a important part of speech signal processing, is a method which transforms the source speech to converted speech with character information of target speaker, and in voice conversion, the semantic content and environment information of source speaker are remained.Voice conversion refers to signal processing, artificial intelligence, acoustics and other fields. It is a typical creature of subjects crossing and has closely relationship with speech recognition, coding, and synthesis, as well as there is resemblance between voice conversion and speaker verification/recognition. Voice conversion is a new research hotspot after speech recognition, speaker verification in speech signal processing field, and it has splendid future of application. This article dwells on the arithmetic research and development of voice conversion for its realization, and supply a reference for arithmetic research of voice conversion system. This article mainly completes the calculation of speech character parameters and research of conversion method of voice conversion.In various speech character parameters, formant frequency, bandwidth and pitch frequency are chosen as voice character parameters. The reasons are as follows: hearing apperceive experiments indicates that formant frequency can stand for a majority of voice information, while average pitch frequency can explain 55% ability of speaker verification. Formant parameters can be calculated with typical linear predict extract method, as formant is a veracious simulation of track. Formant parameters can be used to describe various phenomenon of nature speech stream and synthesis voice with high quality. Pitch frequency is one of the most important parameters of speech signal, and it describes the stimulate source character of voice. Carrying the information of content, it has the function of content verification. This article compares various method of formant parameters calculation, and completes the calculation of the 5 former formant frequencies and bands. As pitch frequency...