Anastasia Kuznetsova

About me

Welcome to my personal website. My name is Anastasia and I am a PhD Candidate in Computer Science and Computational Lingustics at Indiana University Bloomington. I am a part of Prof. Minje Kim's Signals and AI Group in Engineering (SAIGE). My research focuses on model complexity reduction and data efficiency for speech and audio deep learning systems using discrete representations and neural codecs. During my PhD I have worked with speech recognition, speech enhancement, voice conversion among other applications as well as foundational models for multi-channel audio.

As a computational linguist I worked with Prof. Francis Tyers on the improvement of low-resource speech secognition systems and computational morphology.

Publications

• The Potential of Neural Speech Synthesis-Based Data Augmentation for Personalized Speech Enhancement, Anastasia Kuznetsova, Aswin Siwaraman, Minje Kim - International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2023.
• Curriculum optimization for low-resource speech recognition, Anastasia Kuznetsova, Anurag Kumar, Jennifer Drexler-Fox and Francis Tyers - International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2022.
• Optimally Encoding Inductive Biases into the Transformer Improves End-to-End Speech Translation, Piyush Vyas, Anastasia Kuznetsova, Donald S. Williamson - INTERSPEECH 2021 (Best Student Paper Award 🏆 ).
• A finite-state morphological analyser for Paraguayan Guaraní,Anastasia Kuznetsova, Francis Tyers - Proc. of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas 2020.
• A finite-state morphological analyser for Evenki, Anna Zueva, Anastasia Kuznetsova, Francis Tyers - Proc. of The International Conference on Language Resources and Evaluation (LREC) 2020.

Education

Curriculum Vitae

You can download my CV by clicking the link below: