%Aigaion2 BibTeX export from Idiap Publications
%Friday 14 March 2025 01:30:59 AM

@INPROCEEDINGS{Purohit_ICASSP-2_2025,
         author = {Purohit, Tilak and Magimai-Doss, Mathew},
       keywords = {ASR, domain adaptation, Finetuning, Foundation Models, Speech Emotion Recognition, wav2vec2.0},
       projects = {EMIL},
          month = apr,
          title = {Emotion information recovery potential of wav2vec2 network fine-tuned for speech recognition task},
      booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
           year = {2025},
      publisher = {IEEE},
       location = {Hyderabad, India},
       abstract = {Fine-tuning has become a norm to achieve state-of-the-art performance when employing pre-trained networks like foundation models. These models are typically pre-trained on large-scale unannotated data using self-supervised learning (SSL) methods. The SSL-based pre-training on large-scale data enables the network to learn the inherent structure/properties of the data, providing it with capabilities in generalization and knowledge transfer for various downstream tasks. However, when fine-tuned for a specific task, these models become task-specific. Finetuning may cause distortions in the patterns learned by the network during pre-training.  In this work, we investigate these distortions by analyzing the network's information recovery capabilities by designing a study where speech emotion recognition is the target task and automatic speech recognition is an intermediary task. 
We show that the network recovers the task-specific information but with a shift in the decisions also through attention analysis, we demonstrate some layers do not recover the information fully.},
            pdf = {https://publications.idiap.ch/attachments/papers/2025/Purohit_ICASSP-2_2025.pdf}
}