%0 Conference Paper %1 conf/interspeech/Bhati0MTD23 %A Bhati, Saurabhchand %A Villalba, Jesús %A Moro-Velázquez, Laureano %A Thebaud, Thomas %A Dehak, Najim %B INTERSPEECH %D 2023 %E Harte, Naomi %E Carson-Berndsen, Julie %E Jones, Gareth %I ISCA %K dblp %P 431-435 %T Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning. %U http://dblp.uni-trier.de/db/conf/interspeech/interspeech2023.html#Bhati0MTD23

@inproceedings{conf/interspeech/Bhati0MTD23, added-at = {2024-06-14T00:00:00.000+0200}, author = {Bhati, Saurabhchand and Villalba, Jesús and Moro-Velázquez, Laureano and Thebaud, Thomas and Dehak, Najim}, biburl = {https://www.bibsonomy.org/bibtex/28523847c678158aea79b4e25134ef053/dblp}, booktitle = {INTERSPEECH}, crossref = {conf/interspeech/2023}, editor = {Harte, Naomi and Carson-Berndsen, Julie and Jones, Gareth}, ee = {https://doi.org/10.21437/Interspeech.2023-135}, interhash = {663bf0f18092234813a26abde31009b7}, intrahash = {8523847c678158aea79b4e25134ef053}, keywords = {dblp}, pages = {431-435}, publisher = {ISCA}, timestamp = {2024-06-17T07:31:44.000+0200}, title = {Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning.}, url = {http://dblp.uni-trier.de/db/conf/interspeech/interspeech2023.html#Bhati0MTD23}, year = 2023 }