Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to two main factors: the first is the big gap among the source and the target domain distributions; the second factor is the major availability of unlabeled utterances in contrast to the labeled ones for the new language. Taking into account previous aspects, we propose a Semi-Supervised Learning (SSL) method for cross-lingual emotion recognition when only few labeled examples in the target domain (i.e. the new language) are available. Our method is based on a Transformer and it adapts to the new domain by exploiting a pseudo-labeling strategy on the unlabeled utterances. In particular, the use of a hard and soft pseudo-labels approach is investigated. We thoroughly evaluate the performance of the proposed method in a speaker-independent setup on both the source and the new language and show its robustness across five languages belonging to different linguistic strains. The experimental findings indicate that the unweighted accuracy is increased by an average of 40% compared to state-of-the-art methods.
Agarla, M., Bianco, S., Celona, L., Napoletano, P., Petrovsky, A., Piccoli, F., et al. (2024). Semi-supervised cross-lingual speech emotion recognition. EXPERT SYSTEMS WITH APPLICATIONS, 237(Part A (1 March 2024)) [10.1016/j.eswa.2023.121368].
Semi-supervised cross-lingual speech emotion recognition
Agarla, Mirko;Bianco, Simone;Celona, Luigi
;Napoletano, Paolo;Piccoli, Flavio;Schettini, Raimondo;
2024
Abstract
Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to two main factors: the first is the big gap among the source and the target domain distributions; the second factor is the major availability of unlabeled utterances in contrast to the labeled ones for the new language. Taking into account previous aspects, we propose a Semi-Supervised Learning (SSL) method for cross-lingual emotion recognition when only few labeled examples in the target domain (i.e. the new language) are available. Our method is based on a Transformer and it adapts to the new domain by exploiting a pseudo-labeling strategy on the unlabeled utterances. In particular, the use of a hard and soft pseudo-labels approach is investigated. We thoroughly evaluate the performance of the proposed method in a speaker-independent setup on both the source and the new language and show its robustness across five languages belonging to different linguistic strains. The experimental findings indicate that the unweighted accuracy is increased by an average of 40% compared to state-of-the-art methods.File | Dimensione | Formato | |
---|---|---|---|
Agarla-2024-Expert Systems with Applications-VoR.pdf
accesso aperto
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Creative Commons
Dimensione
2.8 MB
Formato
Adobe PDF
|
2.8 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.