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

The capability of generating speech with specific type of emotion is desiredfor many applications of human-computer interaction. Cross-speaker emotiontransfer is a common approach to generating emotional speech when speech withemotion labels from target speakers is not available for model training. Thispaper presents a novel cross-speaker emotion transfer system, named iEmoTTS.The system is composed of an emotion encoder, a prosody predictor, and a timbreencoder. The emotion encoder extracts the identity of emotion type as well asthe respective emotion intensity from the mel-spectrogram of input speech. Theemotion intensity is measured by the posterior probability that the inpututterance carries that emotion. The prosody predictor is used to provideprosodic features for emotion transfer. The timber encoder providestimbre-related information for the system. Unlike many other studies whichfocus on disentangling speaker and style factors of speech, the iEmoTTS isdesigned to achieve cross-speaker emotion transfer via disentanglement betweenprosody and timbre. Prosody is considered as the main carrier ofemotion-related speech characteristics and timbre accounts for the essentialcharacteristics for speaker identification. Zero-shot emotion transfer, meaningthat speech of target speakers are not seen in model training, is also realizedwith iEmoTTS. Extensive experiments of subjective evaluation have been carriedout. The results demonstrate the effectiveness of iEmoTTS as compared withother recently proposed systems of cross-speaker emotion transfer. It is shownthat iEmoTTS can produce speech with designated emotion type and controllableemotion intensity. With appropriate information bottleneck capacity, iEmoTTS isable to effectively transfer emotion information to a new speaker. Audiosamples are publicly available https://patrick-g-zhang.github.io/iemotts/

iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre