Tacotron: Towards End-to-end Speech Synthesis

Abstract

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this challenging task. Tacotron achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness. In addition, since Tacotron generates speech at the frame level, it's substantially faster than sample-level autoregressive methods.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2017tacotron

Related papers

• Wave-tacotron: Spectrogram-free End-to-end Text-to-speech Synthesis (2020)12.81
• Parallel Tacotron: Non-autoregressive And Controllable TTS (2020)12.54
• Semi-supervised Training For Improving Data Efficiency In End-to-end Speech Synthesis (2018)13.28
• Non-attentive Tacotron: Robust And Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling (2020)0.00
• Investigation Of Enhanced Tacotron Text-to-speech Synthesis Systems With Self-attention For Pitch Accent Language (2018)12.54
• Towards End-to-end Prosody Transfer For Expressive Speech Synthesis With Tacotron (2018)0.00
• Audiovisual Speech Synthesis Using Tacotron2 (2020)8.09
• Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions (2017)24.07