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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present the JVNV, a Japanese emotional speech corpus with verbal contentand nonverbal vocalizations whose scripts are generated by a large-scalelanguage model. Existing emotional speech corpora lack not only properemotional scripts but also nonverbal vocalizations (NVs) that are essentialexpressions in spoken language to express emotions. We propose an automaticscript generation method to produce emotional scripts by providing seed wordswith sentiment polarity and phrases of nonverbal vocalizations to ChatGPT usingprompt engineering. We select 514 scripts with balanced phoneme coverage fromthe generated candidate scripts with the assistance of emotion confidencescores and language fluency scores. We demonstrate the effectiveness of JVNV byshowing that JVNV has better phoneme coverage and emotion recognizability thanprevious Japanese emotional speech corpora. We then benchmark JVNV on emotionaltext-to-speech synthesis using discrete codes to represent NVs. We show thatthere still exists a gap between the performance of synthesizing read-aloudspeech and emotional speech, and adding NVs in the speech makes the task evenharder, which brings new challenges for this task and makes JVNV a valuableresource for relevant works in the future. To our best knowledge, JVNV is thefirst speech corpus that generates scripts automatically using large languagemodels.

JVNV: A Corpus of Japanese Emotional Speech with Verbal Content and Nonverbal Expressions