Integrated speaker-adaptive speech synthesis


Samples to support the ASRU 2017 submission titled above.

This page contains the following samples:

  • Original: Natural Recording Speech
  • Baseline: GMM-based i-vector independent extraction
  • IIE: Integrated iVector extraction, with flat attention weights
  • IIEA: Integrated iVector extraction with attention mechanism

  • originalbaselineIIEIIEA
    female_1
    female_2
    female_3
    male_1
    male_2