A Layer-anchoring Strategy For Enhancing Cross-lingual Speech Emotion Recognition

Abstract

Cross-lingual speech emotion recognition (SER) is important for a wide range of everyday applications. While recent SER research relies heavily on large pretrained models for emotion training, existing studies often concentrate solely on the final transformer layer of these models. However, given the task-specific nature and hierarchical architecture of these models, each transformer layer encapsulates different levels of information. Leveraging this hierarchical structure, our study focuses on the information embedded across different layers. Through an examination of layer feature similarity across different languages, we propose a novel strategy called a layer-anchoring mechanism to facilitate emotion transfer in cross-lingual SER tasks. Our approach is evaluated using two distinct language affective corpora (MSP-Podcast and BIIC-Podcast), achieving a best UAR performance of 60.21% on the BIIC-podcast corpus. The analysis uncovers interesting insights into the behavior of popular pr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyupadhyay2024a

Related papers

• Mouth Articulation-based Anchoring For Improved Cross-corpus Speech Emotion Recognition (2024)2.26
• Decoding Emotions: A Comprehensive Multilingual Study Of Speech Models For Speech Emotion Recognition (2023)0.00
• Cross-lingual Speech Emotion Recognition: Humans Vs. Self-supervised Models (2024)5.84
• Semi-supervised Cross-lingual Speech Emotion Recognition (2022)10.85
• Multilingual Speech Emotion Recognition With Multi-gating Mechanism And Neural Architecture Search (2022)2.26
• Leveraging Cross-attention Transformer And Multi-feature Fusion For Cross-linguistic Speech Emotion Recognition (2025)4.52
• Multistage Linguistic Conditioning Of Convolutional Layers For Speech Emotion Recognition (2021)9.23
• Towards Interpretable And Transferable Speech Emotion Recognition: Latent Representation Based Analysis Of Features, Methods And Corpora (2021)0.00