← Search

Mark Anderson

2 accepted papers

2023

Learnable Frontends That Do Not Learn: Quantifying Sensitivity To Filterbank Initialisation

ICASSP 2023accepted

While much of modern speech and audio processing relies on deep neural networks trained using fixed audio representations, recent studies suggest great potential in acoustic frontends learnt jointly with a backend. In this study, we focus specifically on learnable filterbanks. Prior studies have rep…

Cited by 0SourceScholar
2021

Replicating and Extending “Because Their Treebanks Leak”: Graph Isomorphism, Covariants, and Parser Performance

ACL 2021short

Søgaard (2020) obtained results suggesting the fraction of trees occurring in the test data isomorphic to trees in the training set accounts for a non-trivial variation in parser performance. Similar to other statistical analyses in NLP, the results were based on evaluating linear regressions. Howev…

Cited by 6SourcePDFScholar