Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Isaac Elias, Heiga Zen, Jonathan Shen, Yu Zhang, Jia Ye, RJ Skerry-Ryan, Yonghui Wu
Abstract
This paper introduces Parallel Tacotron 2, a non-autoregressive neural text-to-speech model with a fully differentiable duration model which does not require supervised duration signals.The duration model is based on a novel attention mechanism and an iterative reconstruction loss based on Soft Dynamic Time Warping, this model can learn token-frame alignments as well as token durations automatically.Experimental results show that Parallel Tacotron 2 outperforms baselines in subjective naturalness in several diverse multi speaker evaluations.
Topics & Concepts
Duration (music)Autoregressive modelComputer scienceNaturalnessCorrectnessSecurity tokenDifferentiable functionImage warpingSpeech recognitionAbstractionArtificial intelligenceFrame (networking)AlgorithmMathematicsStatisticsComputer securityPhilosophyEpistemologyMathematical analysisPhysicsTelecommunicationsArtLiteratureQuantum mechanicsSpeech Recognition and SynthesisMusic and Audio ProcessingNatural Language Processing Techniques