Sarthak Yadav

Employment

• Aalborg University PhD Fellow
  2022 - Present
• Pioneer Center for AI PhD fellow
  2022 - Present
• Idiap Research Institute Research Intern
  2022 - 2022
• Staqu Technologies Lead Research Engineer
  2017 - 2021
• Aalborg University

Education

• University of Glasgow MSc Research in Computing Science
  2021 - Present
• Krishna Institute of Engineering & Technology Bachelor of Technology in Computer Science and Engineering
  2013 - 2017

Projects & Funding

Projects & funding information is unavailable.

Publications (17)

• Temporal Pooling Strategies for Training-Free Anomalous Sound Detection with Self-Supervised Audio Embeddings
  2026 DOI: 10.48550/arxiv.2603.04605
  +Save
• AudioMAE++
  2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP) 2025 DOI: 10.1109/MLSP62443.2025.11204339
  +Save
• AxLSTMs
  Interspeech 2025 2025 DOI: 10.21437/Interspeech.2025-426
  +Save
• Learning Self-Supervised General Audio Representations from Masked Spectrograms
  Ph.d.-serien for Det Tekniske Fakultet for IT og Design, Aalborg Universitet 2025 DOI: 10.54337/aau819588501
  +Save
• Audio Mamba
  Interspeech 2024 2024 DOI: 10.21437/Interspeech.2024-1274
  +Save
• Audio xLSTMs
  2024 DOI: 10.48550/arXiv.2408.16568
  +Save
• Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
  The Twelfth International Conference on Learning Representations 2024
  +Save
• Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
  2023 DOI: 10.48550/arXiv.2306.00561
  +Save
• Towards Learning Emotion Information from Short Segments of Speech
  ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings 2023 DOI: 10.1109/ICASSP49357.2023.10095892
  +Save
• Comparing Biosignal and Acoustic feature Representation for Continuous Emotion Recognition
  MuSe 2022 - Proceedings of the 3rd International Multimodal Sentiment Analysis Workshop and Challenge 2022 DOI: 10.1145/3551876.3554812
  +Save
• Learning neural audio features without supervision
  Interspeech 2022 2022 DOI: 10.21437/interspeech.2022-10834
  +Save
• GISE-51: A scalable isolated sound events dataset
  2021
  +Save
• End-to-End Bengali Speech Recognition
  2020
  +Save
• Frequency and Temporal Convolutional Attention for Text-Independent Speaker Recognition
  ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2020 DOI: 10.1109/ICASSP40776.2020.9054440
  +Save
• Prediction of ubiquitination sites using UbiNets
  Sarthak Yadav, Manoj Gupta, Ankur Singh Bist
  Advances in Fuzzy Systems 2020 DOI: 10.1155/2018/5125103
  +Save
• Residual nets for understanding animal behavior
  Sarthak Yadav, Ankur Singh Bist
  Journal of Animal Behaviour and Biometeorology 2019 DOI: 10.31893/2318-1265jabb.v7n2p97-103
  +Save
• Learning discriminative features for speaker identification and verification
  Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2018 DOI: 10.21437/Interspeech.2018-1015
  +Save