A method of creating a new speaker²s voicefont in a text-to-speech system
نویسندگان
چکیده
This paper presents a method of creating a new speaker’s voice database (VoiceFont) by which the voice of the donor speaker can be synthesized for mimicking in a text-to-speech system. A VoiceFont creation system, “VoiceFont Builder”, is developed to make the creation process easier and more effective than current systems. The voice feature extraction applied in the system is a simple but powerful method that makes the most of the target speech synthesizer. Using a VoiceFont obtained, we conducted experiments on F0 contour generation in view of reproducing that of the donor speaker’s voice.
منابع مشابه
Speaker recognizability evaluation of a voicefont-based text-to-speech system
We have developed a new text-to-speech system based on the VoiceFont technology. A VoiceFont is a voice dictionary for speech synthesis that holds the acoustic and prosodic characteristics extracted from the voice corpus of a speaker. The text-to-speech system using a VoiceFont is able to synthetically mimic the voice of the donor speaker. In this paper, we evaluated speaker recognizability of ...
متن کاملA VoiceFont Creation Framework for Generating Personalized Voices
This paper presents a new framework for effectively creating VoiceFonts for speech synthesis. A VoiceFont in this paper represents a voice inventory aimed at generating personalized voices. Creating wellformed voice inventories is a time-consuming and laborious task. This has become a critical issue for speech synthesis systems that make an attempt to synthesize many high quality voice personal...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملCipher text only attack on speech time scrambling systems using correction of audio spectrogram
Recently permutation multimedia ciphers were broken in a chosen-plaintext scenario. That attack models a very resourceful adversary which may not always be the case. To show insecurity of these ciphers, we present a cipher-text only attack on speech permutation ciphers. We show inherent redundancies of speech can pave the path for a successful cipher-text only attack. To that end, regularities ...
متن کامل