Fastmandarin: Efficient Local Modeling for Natural Mandarin Speech Synthesis

Abstract

Attention-based speech synthesis methods often suffer from dispersed attention across the entire input sequence, resulting in poor local modeling and unnatural Mandarin synthesized speech. To address these issues, we present FastMandarin, a rapid and natural Mandarin speech synthesis framework that employs two explicit methods to enhance local modeling and improve pronunciation representation. Firstly, we tag Chinese characters to delineate phrase boundaries within a sentence, and these tags are integrated into the network’s hidden layer features at each time step, effectively bolstering local contributions in latent representations. Secondly, we introduce a multi-scale context feature extractor network that employs parallel convolution with various filters. Additionally, we optimize duration alignment and Mel-spectrogram reconstruction to enhance overall performance. Experimental results demonstrate that FastMandarin excels in local modeling, delivering robust Mandarin speech synthesis results.