Search

Current filters:

Current filters:

Author

Subject

Date issued

Has File(s)

Search Results

Results 1-1 of 1 (Search time: 0.001 seconds).
  • <<
  • 1
  • >>
    • Investigations on speaker adaptation using a continuous vocoder within recurrent neural network based text-to-speech synthesis
    Authors: Ali Raheem, Mandeel; Mohammed Salah, Al-Radhi; Tamás Gábor, Csapó;  Advisor: -;  Co-Author: - (2023)

    This paper presents an investigation of speaker adaptation using a continuous vocoder for parametric text-to-speech (TTS) synthesis. In purposes that demand low computational complexity, conventional vocoder-based statistical parametric speech synthesis can be preferable. While capable of remarkable naturalness, recent neural vocoders nonetheless fall short of the criteria for real-time synthesis. We investigate our former continuous vocoder, in which the excitation is characterized employing two one-dimensional parameters: Maximum Voiced Frequency and continuous fundamental frequency (F0).