Scholarlink

Transformer-based architectures have made significant progress in speech emotion recognition (SER). However, most published SER research trained and tested models on data from the same corpus, resulting in poor generalisation ability to unseen data collected from different corpora. To address this, we applied the HuBERT model to a combined training set consisting of five publicly available datasets (IEMOCAP, RAVDESS, TESS, CREMA-D, and \(80\%\) CMU-MOSEI) and conducted cross-corpus testing on the Strong Emotion (StrEmo) Dataset (a natural dataset collected by the authors) and two publicly available datasets (SAVEE and \(20\%\) CMU-MOSEI). Our best result achieved an F1 score of 0.78 over the three test sets, with an F1 score of 0.86 for StrEmo specifically. Additionally, we are pleased to release the spreadsheet of key information on the StrEmo dataset as supplementary material to the conference.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Investigating HuBERT-Based Speech Emotion Recognition Generalisation Capability

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Letian Li,
  • Cornelius Glackin,
  • Nigel Cannings,
  • Vito Veneziano,
  • Jack Barker,
  • Olakunle Oduola,
  • Chris Woodruff,
  • Thea Laird,
  • James Laird,
  • Yi Sun

摘要

Transformer-based architectures have made significant progress in speech emotion recognition (SER). However, most published SER research trained and tested models on data from the same corpus, resulting in poor generalisation ability to unseen data collected from different corpora. To address this, we applied the HuBERT model to a combined training set consisting of five publicly available datasets (IEMOCAP, RAVDESS, TESS, CREMA-D, and \(80\%\) CMU-MOSEI) and conducted cross-corpus testing on the Strong Emotion (StrEmo) Dataset (a natural dataset collected by the authors) and two publicly available datasets (SAVEE and \(20\%\) CMU-MOSEI). Our best result achieved an F1 score of 0.78 over the three test sets, with an F1 score of 0.86 for StrEmo specifically. Additionally, we are pleased to release the spreadsheet of key information on the StrEmo dataset as supplementary material to the conference.