Non-attentive Tacotron: Robust And Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling

Abstract

This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model, replacing the attention mechanism with an explicit duration predictor. This improves robustness significantly as measured by unaligned duration ratio and word deletion rate, two metrics introduced in this paper for large-scale robustness evaluation using a pre-trained speech recognition model. With the use of Gaussian upsampling, Non-Attentive Tacotron achieves a 5-scale mean opinion score for naturalness of 4.41, slightly outperforming Tacotron 2. The duration predictor enables both utterance-wide and per-phoneme control of duration at inference time. When accurate target durations are scarce or unavailable in the training data, we propose a method using a fine-grained variational auto-encoder to train the duration predictor in a semi-supervised or unsupervised manner, with results almost as good as supervised training.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshen2020non

Related papers

• Parallel Tacotron 2: A Non-autoregressive Neural TTS Model With Differentiable Duration Modeling (2021)12.68
• Parallel Tacotron: Non-autoregressive And Controllable TTS (2020)12.54
• Tacotron: Towards End-to-end Speech Synthesis (2017)0.00
• Non-autoregressive TTS With Explicit Duration Modelling For Low-resource Highly Expressive Speech (2021)8.82
• Semi-supervised Training For Improving Data Efficiency In End-to-end Speech Synthesis (2018)13.28
• Regotron: Regularizing The Tacotron2 Architecture Via Monotonic Alignment Loss (2022)5.24
• Controllable Neural Text-to-speech Synthesis Using Intuitive Prosodic Features (2020)11.76
• Towards End-to-end Prosody Transfer For Expressive Speech Synthesis With Tacotron (2018)0.00