Discriminative acoustic word embeddings: Tecurrent neural network-based approaches S Settle, K Livescu 2016 IEEE Spoken Language Technology Workshop (SLT), 503-510, 2016 | 108 | 2016 |
Query-by-example search with discriminative neural acoustic word embeddings S Settle, K Levin, H Kamper, K Livescu arXiv preprint arXiv:1706.03818, 2017 | 98 | 2017 |
End-to-end multi-speaker speech recognition S Settle, J Le Roux, T Hori, S Watanabe, JR Hershey 2018 IEEE international conference on acoustics, speech and signal …, 2018 | 90 | 2018 |
Methods and systems for recognizing simultaneous speech by multiple speakers J Le Roux, T Hori, S Settle, H Seki, S Watanabe, J Hershey US Patent 10,811,000, 2020 | 71 | 2020 |
Visually grounded learning of keyword prediction from untranscribed speech H Kamper, S Settle, G Shakhnarovich, K Livescu arXiv preprint arXiv:1703.08136, 2017 | 68 | 2017 |
Acoustically grounded word embeddings for improved acoustics-to-word speech recognition S Settle, K Audhkhasi, K Livescu, M Picheny ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 40 | 2019 |
Multilingual jointly trained acoustic and written word embeddings Y Hu, S Settle, K Livescu arXiv preprint arXiv:2006.14007, 2020 | 27 | 2020 |
What do self-supervised speech models know about words? A Pasad, CM Chien, S Settle, K Livescu Transactions of the Association for Computational Linguistics 12, 372-391, 2024 | 23 | 2024 |
Acoustic span embeddings for multilingual query-by-example search Y Hu, S Settle, K Livescu 2021 IEEE Spoken Language Technology Workshop (SLT), 935-942, 2021 | 14 | 2021 |
Whole-word segmental speech recognition with acoustic word embeddings B Shi, S Settle, K Livescu 2021 IEEE Spoken Language Technology Workshop (SLT), 164-171, 2021 | 9 | 2021 |
Recognition of out-of-vocabulary in direct acoustics-to-word speech recognition using acoustic word embedding K Audhkhasi, K Livescu, M Picheny, S Settle US Patent 10,839,792, 2020 | 2 | 2020 |
Neural approaches to spoken content embedding S Settle arXiv preprint arXiv:2308.14905, 2023 | | 2023 |