Abstract
To be able to interact better with humans, it is crucial for machines to understand sound – a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic semantic similarity assessment. In this work, we treat sound as a first-class citizen, studying downstream 6textual tasks which require aural grounding. To this end, we propose sound-word2vec – a new embedding scheme that learns specialized word embeddings grounded in sounds. For example, we learn that two seemingly (semantically) unrelated concepts, like leaves and paper are similar due to the similar rustling sounds they make. Our embeddings prove useful in textual tasks requiring aural reasoning like text-based sound retrieval and discovering Foley sound effects (used in movies). Moreover, our embedding space captures interesting dependencies between words and onomatopoeia and outperforms prior work on aurally-relevant word relatedness datasets such as AMEN and ASLex.- Anthology ID:
- D17-1096
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 920–925
- Language:
- URL:
- https://aclanthology.org/D17-1096
- DOI:
- 10.18653/v1/D17-1096
- Cite (ACL):
- Ashwin Vijayakumar, Ramakrishna Vedantam, and Devi Parikh. 2017. Sound-Word2Vec: Learning Word Representations Grounded in Sounds. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 920–925, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Sound-Word2Vec: Learning Word Representations Grounded in Sounds (Vijayakumar et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/D17-1096.pdf