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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recently, leveraging BERT pre-training to improve the phoneme encoder in textto speech (TTS) has drawn increasing attention. However, the works applypre-training with character-based units to enhance the TTS phoneme encoder,which is inconsistent with the TTS fine-tuning that takes phonemes as input.Pre-training only with phonemes as input can alleviate the input mismatch butlack the ability to model rich representations and semantic information due tolimited phoneme vocabulary. In this paper, we propose MixedPhoneme BERT, anovel variant of the BERT model that uses mixed phoneme and sup-phonemerepresentations to enhance the learning capability. Specifically, we merge theadjacent phonemes into sup-phonemes and combine the phoneme sequence and themerged sup-phoneme sequence as the model input, which can enhance the modelcapacity to learn rich contextual representations. Experiment resultsdemonstrate that our proposed Mixed-Phoneme BERT significantly improves the TTSperformance with 0.30 CMOS gain compared with the FastSpeech 2 baseline. TheMixed-Phoneme BERT achieves 3x inference speedup and similar voice quality tothe previous TTS pre-trained model PnG BERT

Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech