Speech synthesis using Mel-Cepstral coefficient feature

Wang, Lu

Permalink

https://hdl.handle.net/2142/100043 Copy

Description

Title

Speech synthesis using Mel-Cepstral coefficient feature

Author(s)

Wang, Lu

Contributor(s)

Hasegawa-Johnson, Mark

Issue Date

2018-05

Keyword(s)

• Speech Synthesis
• Cepstrum Analysis

Abstract

This thesis presents a method to improve quality of synthesized speech by reducing the vocoded effect. The synthesis model takes mel-cepstral coefficients and spectrum envelopes as features of the original speech waveform. Mel-cepstral coefficients could be used to generate natural sounding voice and reduce the artificial effect. Compared to regular linear predictive coding (LPC) coefficient which is also widely used in speech synthesis, the mel-cepstral coefficient could resemble the human voice more closely by providing the synthesized speech with more details in the low frequency band. The model uses a synthesis filter to estimate the log spectrum including both zeros and poles in the transfer function, along with the mixed excitation technique which could divide speech signals into multiple frequency bands to better approximate natural speech production.

Type of Resource

text

Language

en

Permalink

http://hdl.handle.net/2142/100043

Owning Collections