UFANS: U-shaped Fully-parallel Acoustic Neural Structure For Statistical Parametric Speech Synthesis With 20X Faster

Abstract

Neural networks with Auto-regressive structures, such as Recurrent Neural Networks (RNNs), have become the most appealing structures for acoustic modeling of parametric text to speech synthesis (TTS) in ecent studies. Despite the prominent capacity to capture long-term dependency, these models consist of massive sequential computations that cannot be fully parallel. In this paper, we propose a U-shaped Fully-parallel Acoustic Neural Structure (UFANS), which is a deconvolutional alternative of RNNs for Statistical Parametric Speech Synthesis (SPSS). The experiments verify that our proposed model is over 20 times faster than RNN based acoustic model, both training and inference on GPU with comparable speech quality. Furthermore, We also investigate that how long information dependence really matters to synthesized speech quality.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyma2018ufans

Related papers

• FPETS : Fully Parallel End-to-end Text-to-speech System (2018)4.52
• Fast, Compact, And High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers For Mobile Devices (2016)13.05
• UL-UNAS: Ultra-lightweight U-nets For Real-time Speech Enhancement Via Network Architecture Search (2025)10.26
• Investigating Gated Recurrent Neural Networks For Speech Synthesis (2016)0.00
• Fast And High-quality Auto-regressive Speech Synthesis Via Speculative Decoding (2024)5.24
• Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder (2016)0.00
• Efficient Neural Audio Synthesis (2018)0.00
• Deep Feed-forward Sequential Memory Networks For Speech Synthesis (2018)5.84