Interspeech 2021 2021
DOI: 10.21437/interspeech.2021-245
|View full text |Cite
|
Sign up to set email alerts
|

Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset

Abstract: Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained on that data. We introduce Spoken ObjectNet, which is designed to remove some of these biases and provide a way to better evaluate how effectively models will perform in real-world scenarios. This dataset expands upon ObjectNet, which is a biascontrolled image dataset that fe… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 17 publications
0
1
0
Order By: Relevance
“…Unlike these works, we directly use semantic context or concept clues obtained from audio-visual learning. Many researchers have proposed unsupervised spoken language learning methods that can learn meaningful audio-visual correspondences from visually grounded speech [6,13,15,26,27,30,31,35,36,38,39,41,47]. [15] proposed a multiple-encoder model to associate visual objects with spoken words and showed a similarity profile between an image and its spoken caption.…”
Section: Related Workmentioning
confidence: 99%
“…Unlike these works, we directly use semantic context or concept clues obtained from audio-visual learning. Many researchers have proposed unsupervised spoken language learning methods that can learn meaningful audio-visual correspondences from visually grounded speech [6,13,15,26,27,30,31,35,36,38,39,41,47]. [15] proposed a multiple-encoder model to associate visual objects with spoken words and showed a similarity profile between an image and its spoken caption.…”
Section: Related Workmentioning
confidence: 99%