English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Text to speech (TTS) and automatic speech recognition (ASR) are two dualtasks in speech processing and both achieve impressive performance thanks tothe recent advance in deep learning and large amount of aligned speech and textdata. However, the lack of aligned data poses a major practical problem for TTSand ASR on low-resource languages. In this paper, by leveraging the dual natureof the two tasks, we propose an almost unsupervised learning method that onlyleverages few hundreds of paired data and extra unpaired data for TTS and ASR.Our method consists of the following components: (1) a denoising auto-encoder,which reconstructs speech and text sequences respectively to develop thecapability of language modeling both in speech and text domain; (2) dualtransformation, where the TTS model transforms the text $y$ into speech$\hat{x}$, and the ASR model leverages the transformed pair $(\hat{x},y)$ fortraining, and vice versa, to boost the accuracy of the two tasks; (3)bidirectional sequence modeling, which addresses error propagation especiallyin the long speech and text sequence when training with few paired data; (4) aunified model structure, which combines all the above components for TTS andASR based on Transformer model. Our method achieves 99.84% in terms of wordlevel intelligible rate and 2.68 MOS for TTS, and 11.7% PER for ASR on LJSpeechdataset, by leveraging only 200 paired speech and text data (about 20 minutesaudio), together with extra unpaired speech and text data.

Almost Unsupervised Text to Speech and Automatic Speech Recognition