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

In this paper, we propose a novel time-frequency joint learning method forspeech emotion recognition, called Time-Frequency Transformer. Its advantage isthat the Time-Frequency Transformer can excavate global emotion patterns in thetime-frequency domain of speech signal while modeling the local emotionalcorrelations in the time domain and frequency domain respectively. For thepurpose, we first design a Time Transformer and Frequency Transformer tocapture the local emotion patterns between frames and inside frequency bandsrespectively, so as to ensure the integrity of the emotion information modelingin both time and frequency domains. Then, a Time-Frequency Transformer isproposed to mine the time-frequency emotional correlations through the localtime-domain and frequency-domain emotion features for learning morediscriminative global speech emotion representation. The whole process is atime-frequency joint learning process implemented by a series of Transformermodels. Experiments on IEMOCAP and CASIA databases indicate that our proposedmethod outdoes the state-of-the-art methods.

Time-Frequency Transformer: A Novel Time Frequency Joint Learning Method for Speech Emotion Recognition