David Harwath

David Harwath

Auto-generated profile, based on publicly available information

David Harwath

The University of Texas at Austin

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2019 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
DHDavid Harwath
David Harwath
ARAdrià Recasens
Adrià Recasens
DSDídac Surís
Dídac Surís
GCGalen Chuang
Galen Chuang
ATAntonio Torralba
Antonio Torralba
JGJames Glass
James Glass
In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis using the Places 205 and ADE20k datasets demonstrating that our models implicitly learn semantically coupled object and word detectors.

6 October 2018
Verified
Book Chapter
Open access
PDF file
DHDavid Harwath
David Harwath
ARAdrià Recasens
Adrià Recasens
DSDídac Surís
Dídac Surís
GCGalen Chuang
Galen Chuang
ATAntonio Torralba
Antonio Torralba
JGJames Glass
James Glass
In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis using the Places 205 and ADE20k datasets demonstrating that our models implicitly learn semantically-coupled object and word detectors.

1 January 2022
Verified
Conference Paper
Open access
PDF file
ADAnuj Diwan
Anuj Diwan
LBLayne Berry
Layne Berry
ECEunsol Choi
Eunsol Choi
DHDavid Harwath
David Harwath
KMKyle Mahowald
Kyle Mahowald
Anuj Diwan, Layne Berry, Eunsol Choi, David Harwath, Kyle Mahowald. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

18 September 2022
Verified
Conference Paper
Open access
PPPuyuan Peng
Puyuan Peng
DHDavid Harwath
David Harwath

1 January 2025
Verified
Conference Paper
Open access
PDF file
ADAnuj Diwan
Anuj Diwan
ZZZhisheng Zheng
Zhisheng Zheng
DHDavid Harwath
David Harwath
ECEunsol Choi
Eunsol Choi
Anuj Diwan, Zhisheng Zheng, David Harwath, Eunsol Choi. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

24 April 2023
Verified
Conference Paper
Closed access
DDDebadatta Dash
Debadatta Dash
PFPaul Ferrari
Paul Ferrari
ABAbbas Babajani-Feremi
Abbas Babajani-Feremi
DHDavid Harwath
David Harwath
ABAmir Borna
Amir Borna
JWJun Wang
Jun Wang
Speech decoding-based brain-computer interfaces (Speech-BCIs) decode speech directly from brain signals, which have the potential to offer faster and natural communication to patients with locked-in syndrome than the current BCI-spellers. On account of the huge cognitive variance among subjects, most of the current speech-BCI models have focused on subject-dependent decoding where the training and evaluation of the decoding algorithms use data from the same participants. These models do not generalize across individuals and, thus, are limited by the small data size that can be obtained from a single participant. Few studies have attempted subject-independent decoding but the performances are sub-par at best and significantly lower than subject-dependent models. To address this issue, we evaluated imagined and overt speech decoding with magnetoencephalography (MEG) recordings of eight speakers in a generalizable subject-independent setting. We used recent domain adaptation techniques including feature augmentation and curriculum learning to introduce generalizability to the decoding model. Our results indicated that domain adaptation techniques can be efficient in subject-independent decoding. The best performance was obtained with a curriculum learning based adaptation technique that resulted in decoding accuracy was close to that in subject-dependent decoding. Our findings show the possibility of subject generalization in neural speech decoding.