Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation

Aparna Balagopalan, Jekaterina Novikova, Matthew B A Mcdermott, Bret Nestor, Tristan Naumann, Marzyeh Ghassemi
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 116:202-219, 2020.

Abstract

Multi-language speech datasets are scarce and often have small sample sizes in the medical domain. Robust transfer of linguistic features across languages could improve rates of early diagnosis and therapy for speakers of low-resource languages when detecting health conditions from speech. We utilize out-of-domain, unpaired, single-speaker, healthy speech data for training multiple Optimal Transport (OT) domain adaptation systems. We learn mappings from other languages to English and detect aphasia from linguistic characteristics of speech, and show that OT domain adaptation improves aphasia detection over unilingual baselines for French (6{%} increased F1) and Mandarin (5{%} increased F1). Further, we show that adding aphasic data to the domain adaptation system significantly increases performance for both French and Mandarin, increasing the F1 scores further (10{%} and 8{%} increase in F1 scores for French and Mandarin, respectively, over unilingual baselines).

Cite this Paper

BibTeX
@InProceedings{pmlr-v116-balagopalan20a, title = {{Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation}}, author = {Balagopalan, Aparna and Novikova, Jekaterina and Mcdermott, Matthew B A and Nestor, Bret and Naumann, Tristan and Ghassemi, Marzyeh}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {202--219}, year = {2020}, editor = {Dalca, Adrian V. and McDermott, Matthew B.A. and Alsentzer, Emily and Finlayson, Samuel G. and Oberst, Michael and Falck, Fabian and Beaulieu-Jones, Brett}, volume = {116}, series = {Proceedings of Machine Learning Research}, month = {13 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v116/balagopalan20a/balagopalan20a.pdf}, url = {https://proceedings.mlr.press/v116/balagopalan20a.html}, abstract = {Multi-language speech datasets are scarce and often have small sample sizes in the medical domain. Robust transfer of linguistic features across languages could improve rates of early diagnosis and therapy for speakers of low-resource languages when detecting health conditions from speech. We utilize out-of-domain, unpaired, single-speaker, healthy speech data for training multiple Optimal Transport (OT) domain adaptation systems. We learn mappings from other languages to English and detect aphasia from linguistic characteristics of speech, and show that OT domain adaptation improves aphasia detection over unilingual baselines for French (6{%} increased F1) and Mandarin (5{%} increased F1). Further, we show that adding aphasic data to the domain adaptation system significantly increases performance for both French and Mandarin, increasing the F1 scores further (10{%} and 8{%} increase in F1 scores for French and Mandarin, respectively, over unilingual baselines).} }
Endnote
%0 Conference Paper %T Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation %A Aparna Balagopalan %A Jekaterina Novikova %A Matthew B A Mcdermott %A Bret Nestor %A Tristan Naumann %A Marzyeh Ghassemi %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Adrian V. Dalca %E Matthew B.A. McDermott %E Emily Alsentzer %E Samuel G. Finlayson %E Michael Oberst %E Fabian Falck %E Brett Beaulieu-Jones %F pmlr-v116-balagopalan20a %I PMLR %P 202--219 %U https://proceedings.mlr.press/v116/balagopalan20a.html %V 116 %X Multi-language speech datasets are scarce and often have small sample sizes in the medical domain. Robust transfer of linguistic features across languages could improve rates of early diagnosis and therapy for speakers of low-resource languages when detecting health conditions from speech. We utilize out-of-domain, unpaired, single-speaker, healthy speech data for training multiple Optimal Transport (OT) domain adaptation systems. We learn mappings from other languages to English and detect aphasia from linguistic characteristics of speech, and show that OT domain adaptation improves aphasia detection over unilingual baselines for French (6{%} increased F1) and Mandarin (5{%} increased F1). Further, we show that adding aphasic data to the domain adaptation system significantly increases performance for both French and Mandarin, increasing the F1 scores further (10{%} and 8{%} increase in F1 scores for French and Mandarin, respectively, over unilingual baselines).
APA
Balagopalan, A., Novikova, J., Mcdermott, M.B.A., Nestor, B., Naumann, T. & Ghassemi, M.. (2020). Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 116:202-219 Available from https://proceedings.mlr.press/v116/balagopalan20a.html.

Related Material