%Aigaion2 BibTeX export from Idiap Publications %Monday 20 January 2025 03:42:50 PM @INPROCEEDINGS{Purohit_ICASSP-4_2025, author = {Purohit, Tilak and Magimai-Doss, Mathew}, projects = {EMIL}, 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}, 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-4_2025.pdf} }