Data-driven formant synthesis
نویسندگان
چکیده
A new approach to formant synthesis, using both rule-based and data-driven methods is presented. Preliminary results from a feasibility study show an advantage in speech quality compared to a rule-based reference system. The method is now being implemented into a general framework.
منابع مشابه
Exploring data driven parametric synthesis
This paper describes our work on building a formant synthesis system based on both rule generated and database driven methods. Three parametric synthesis systems are discussed: our traditional rule based system, a speaker adapted system, and finally a gesture system. The gesture system is a further development of the adapted system in that it includes concatenated formant gestures from a data-d...
متن کاملFormant analysis and synthesis using hidden Markov models
This paper describes a unifying framework for both formant tracking and speech synthesis using Hidden Markov Models (HMM). The feature vector in the HMM is composed by the first three formant frequencies, their bandwidths and their delta with time. Speech is synthesized by generating the most likely sequence of feature vectors from a HMM, trained with a set of sentences from a given speaker. Hi...
متن کاملData-driven Formant Synthesis of Speaker Age
This paper briefly describes the development of a research tool for analysis of speaker age using data-driven formant synthesis. A prototype system was developed to automatically extract 23 acoustic parameters from the Swedish word ‘själen’ [ˈɧɛːlən] (the soul) spoken by four differently aged female speakers of the same dialect and family, and to generate synthetic copies. Functions for paramet...
متن کاملA Data-driven Approach to Source-forma
A data-driven formant-type TTS system is proposed. The formanttype speech synthesizer is one of the most promising architectures to enable flexible control of various voice qualities. By applying the ARX-based speech analysis method, source and formant parameters are automatically obtained. It is shown that a TTS system can be built by using the parameters, without requiring any heuristic rules...
متن کاملF0 and Segment Duration in Formant Synthesis of Speaker Age
This paper describes the work with F0 and segment duration when developing a prototype system for analysis of speaker age using data-driven formant synthesis. The system was developed to extract 23 parameters from the test words—spoken by four differently aged female speakers of the same dialect and family—and to generate synthetic copies. Audio-visual feedback enabled the user to compare the n...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002