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

End-to-end speech synthesis models directly convert the input characters intoan audio representation (e.g., spectrograms). Despite their impressiveperformance, such models have difficulty disambiguating the pronunciations ofidentically spelled words. To mitigate this issue, a separateGrapheme-to-Phoneme (G2P) model can be employed to convert the characters intophonemes before synthesizing the audio. This paper proposes SoundChoice, anovel G2P architecture that processes entire sentences rather than operating atthe word level. The proposed architecture takes advantage of a weightedhomograph loss (that improves disambiguation), exploits curriculum learning(that gradually switches from word-level to sentence-level G2P), and integratesword embeddings from BERT (for further performance improvement). Moreover, themodel inherits the best practices in speech recognition, including multi-tasklearning with Connectionist Temporal Classification (CTC) and beam search withan embedded language model. As a result, SoundChoice achieves a Phoneme ErrorRate (PER) of 2.65% on whole-sentence transcription using data from LibriSpeechand Wikipedia. Index Terms grapheme-to-phoneme, speech synthesis,text-tospeech, phonetics, pronunciation, disambiguation.

SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation