Multilingual acoustic word embeddings for zero-resource languages
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916103024803840 |
|---|---|
| author | Jacobs, Christiaan |
| author_facet | Jacobs, Christiaan |
| contents | This research addresses the challenge of developing speech applications for zero-resource languages that lack labelled data. It specifically uses acoustic word embedding (AWE) -- fixed-dimensional representations of variable-duration speech segments -- employing multilingual transfer, where labelled data from several well-resourced languages are used for pertaining. The study introduces a new neural network that outperforms existing AWE models on zero-resource languages. It explores the impact of the choice of well-resourced languages. AWEs are applied to a keyword-spotting system for hate speech detection in Swahili radio broadcasts, demonstrating robustness in real-world scenarios. Additionally, novel semantic AWE models improve semantic query-by-example search. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10543 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multilingual acoustic word embeddings for zero-resource languages Jacobs, Christiaan Audio and Speech Processing Computation and Language Sound This research addresses the challenge of developing speech applications for zero-resource languages that lack labelled data. It specifically uses acoustic word embedding (AWE) -- fixed-dimensional representations of variable-duration speech segments -- employing multilingual transfer, where labelled data from several well-resourced languages are used for pertaining. The study introduces a new neural network that outperforms existing AWE models on zero-resource languages. It explores the impact of the choice of well-resourced languages. AWEs are applied to a keyword-spotting system for hate speech detection in Swahili radio broadcasts, demonstrating robustness in real-world scenarios. Additionally, novel semantic AWE models improve semantic query-by-example search. |
| title | Multilingual acoustic word embeddings for zero-resource languages |
| topic | Audio and Speech Processing Computation and Language Sound |
| url | https://arxiv.org/abs/2401.10543 |