Efficiently Trained Low-resource Mongolian Text-to-speech System Based On Fullconv-tts

Abstract

Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS model including RNN components has certain requirements for GPU performance and takes a long time. In contrast, studies have shown that CNN-based sequence synthesis technology can greatly reduce training time in text-to-speech models while ensuring a certain performance due to its high parallelism. We propose a new text-to-speech system based on deep convolutional neural networks that does not employ any RNN components (recurrent units). At the same time, we improve the generality and robustness of our model through a series of data augmentation methods such as Time Warping, Frequency Mask, and Time Mask. The final experimental results show that the TTS model using only the CNN component can reduce the training time compared to the classic TTS models such as Tacotron while ensuring the quality of the synthesized

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliang2022efficiently

Related papers

• EM-TTS: Efficiently Trained Low-resource Mongolian Lightweight Text-to-speech (2024)0.00
• Efficiently Trainable Text-to-speech System Based On Deep Convolutional Networks With Guided Attention (2017)16.41
• Non-autoregressive TTS With Explicit Duration Modelling For Low-resource Highly Expressive Speech (2021)8.82
• Towards High-quality Neural TTS For Low-resource Languages By Learning Compact Speech Representations (2022)0.00
• Mntts: An Open-source Mongolian Text-to-speech Synthesis Dataset And Accompanied Baseline (2022)5.24
• Efficienttts: An Efficient And High-quality Text-to-speech Architecture (2020)0.00
• Low-resource Mongolian Speech Synthesis Based On Automatic Prosody Annotation (2022)0.00
• Syncspeech: Efficient And Low-latency Text-to-speech Based On Temporal Masked Transformer (2025)0.00