%Aigaion2 BibTeX export from Idiap Publications
%Friday 10 May 2024 07:10:11 AM

@INPROCEEDINGS{Purohit_ICASSP_2023,
         author = {Purohit, Tilak and Yadav, Sarthak and Vlasenko, Bogdan and Dubagunta, S. Pavankumar and Magimai.-Doss, Mathew},
       keywords = {Convolution Neural Network, end-to-end modelling, Speech Emotion Recognition},
       projects = {EMIL},
          month = jun,
          title = {Towards learning emotion information from short segments of speech},
      booktitle = {International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
           year = {2023},
      publisher = {IEEE},
       location = {Rhodes Island, Greece},
       abstract = {Conventionally, speech emotion recognition has been approached by utterance or turn-level modelling of input signals, either through extracting hand-crafted low-level descriptors, bag-of-audio-words features or by feeding long-duration signals directly to deep neural networks (DNNs). While this approach has been successful, there is a growing interest in modelling speech emotion information at the short segment level, at around 250ms-500ms (e.g. the 2021-22 MuSe Challenges). This paper investigates both hand-crafted feature-based and end-to-end raw waveform DNN approaches for modelling speech emotion information in such short segments.  
Through experimental studies on IEMOCAP corpus, we demonstrate that the end-to-end raw waveform modelling approach is more effective than using hand-crafted features for short-segment level modelling. Furthermore, through relevance signal-based analysis of the trained neural networks, we observe that the top performing end-to-end approach tends to emphasize cepstral information instead of spectral information (such as flux and harmonicity).},
            pdf = {https://publications.idiap.ch/attachments/papers/2023/Purohit_ICASSP_2023.pdf}
}