Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037580942> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3037580942 abstract "Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically grounded word embeddings (AGWEs). Such embeddings have been used to improve speech retrieval, recognition, and spoken term discovery. In this work, we extend this idea to multiple low-resource languages. We jointly train an AWE model and an AGWE model, using phonetically transcribed data from multiple languages. The pre-trained models can then be used for unseen zero-resource languages, or fine-tuned on data from low-resource languages. We also investigate distinctive features, as an alternative to phone labels, to better share cross-lingual information. We test our models on word discrimination tasks for twelve languages. When trained on eleven languages and tested on the remaining unseen language, our model outperforms traditional unsupervised approaches like dynamic time warping. After fine-tuning the pre-trained models on one hour or even ten minutes of data from a new language, performance is typically much better than training on only the target-language data. We also find that phonetic supervision improves performance over character sequences, and that distinctive feature supervision is helpful in handling unseen phones in the target language." @default.
- W3037580942 created "2020-07-02" @default.
- W3037580942 creator A5007445208 @default.
- W3037580942 creator A5015602781 @default.
- W3037580942 creator A5069782842 @default.
- W3037580942 date "2020-06-24" @default.
- W3037580942 modified "2023-09-24" @default.
- W3037580942 title "Multilingual Jointly Trained Acoustic and Written Word Embeddings" @default.
- W3037580942 cites W1524333225 @default.
- W3037580942 cites W1545920196 @default.
- W3037580942 cites W1577418252 @default.
- W3037580942 cites W2025482506 @default.
- W3037580942 cites W2059652594 @default.
- W3037580942 cites W2157331557 @default.
- W3037580942 cites W2166637769 @default.
- W3037580942 cites W2187089797 @default.
- W3037580942 cites W2190506272 @default.
- W3037580942 cites W2291770225 @default.
- W3037580942 cites W2295297373 @default.
- W3037580942 cites W2296681920 @default.
- W3037580942 cites W2407151108 @default.
- W3037580942 cites W2550241133 @default.
- W3037580942 cites W2566587499 @default.
- W3037580942 cites W2578392894 @default.
- W3037580942 cites W2889313720 @default.
- W3037580942 cites W2932675979 @default.
- W3037580942 cites W2962736743 @default.
- W3037580942 cites W2963720603 @default.
- W3037580942 cites W2964121744 @default.
- W3037580942 cites W2970971581 @default.
- W3037580942 cites W3015325583 @default.
- W3037580942 doi "https://doi.org/10.48550/arxiv.2006.14007" @default.
- W3037580942 hasPublicationYear "2020" @default.
- W3037580942 type Work @default.
- W3037580942 sameAs 3037580942 @default.
- W3037580942 citedByCount "2" @default.
- W3037580942 countsByYear W30375809422020 @default.
- W3037580942 countsByYear W30375809422021 @default.
- W3037580942 crossrefType "posted-content" @default.
- W3037580942 hasAuthorship W3037580942A5007445208 @default.
- W3037580942 hasAuthorship W3037580942A5015602781 @default.
- W3037580942 hasAuthorship W3037580942A5069782842 @default.
- W3037580942 hasBestOaLocation W30375809421 @default.
- W3037580942 hasConcept C137293760 @default.
- W3037580942 hasConcept C138885662 @default.
- W3037580942 hasConcept C154945302 @default.
- W3037580942 hasConcept C204321447 @default.
- W3037580942 hasConcept C206345919 @default.
- W3037580942 hasConcept C2524010 @default.
- W3037580942 hasConcept C2776401178 @default.
- W3037580942 hasConcept C2778707766 @default.
- W3037580942 hasConcept C2780861071 @default.
- W3037580942 hasConcept C28490314 @default.
- W3037580942 hasConcept C31258907 @default.
- W3037580942 hasConcept C33923547 @default.
- W3037580942 hasConcept C41008148 @default.
- W3037580942 hasConcept C41895202 @default.
- W3037580942 hasConcept C88516994 @default.
- W3037580942 hasConcept C90805587 @default.
- W3037580942 hasConceptScore W3037580942C137293760 @default.
- W3037580942 hasConceptScore W3037580942C138885662 @default.
- W3037580942 hasConceptScore W3037580942C154945302 @default.
- W3037580942 hasConceptScore W3037580942C204321447 @default.
- W3037580942 hasConceptScore W3037580942C206345919 @default.
- W3037580942 hasConceptScore W3037580942C2524010 @default.
- W3037580942 hasConceptScore W3037580942C2776401178 @default.
- W3037580942 hasConceptScore W3037580942C2778707766 @default.
- W3037580942 hasConceptScore W3037580942C2780861071 @default.
- W3037580942 hasConceptScore W3037580942C28490314 @default.
- W3037580942 hasConceptScore W3037580942C31258907 @default.
- W3037580942 hasConceptScore W3037580942C33923547 @default.
- W3037580942 hasConceptScore W3037580942C41008148 @default.
- W3037580942 hasConceptScore W3037580942C41895202 @default.
- W3037580942 hasConceptScore W3037580942C88516994 @default.
- W3037580942 hasConceptScore W3037580942C90805587 @default.
- W3037580942 hasLocation W30375809421 @default.
- W3037580942 hasOpenAccess W3037580942 @default.
- W3037580942 hasPrimaryLocation W30375809421 @default.
- W3037580942 hasRelatedWork W107051557 @default.
- W3037580942 hasRelatedWork W1491795195 @default.
- W3037580942 hasRelatedWork W2059039199 @default.
- W3037580942 hasRelatedWork W2597757402 @default.
- W3037580942 hasRelatedWork W2806021948 @default.
- W3037580942 hasRelatedWork W2953291251 @default.
- W3037580942 hasRelatedWork W3037580942 @default.
- W3037580942 hasRelatedWork W3095706145 @default.
- W3037580942 hasRelatedWork W3107474891 @default.
- W3037580942 hasRelatedWork W4290682478 @default.
- W3037580942 isParatext "false" @default.
- W3037580942 isRetracted "false" @default.
- W3037580942 magId "3037580942" @default.
- W3037580942 workType "article" @default.