Masked language model scoring J Salazar, D Liang, TQ Nguyen, K Kirchhoff Proceedings of the 58th Annual Meeting of the Association for Computational …, 2020 | 435 | 2020 |
Transformers without tears: Improving the normalization of self-attention TQ Nguyen, J Salazar Proceedings of IWSLT 2019 (the 16th International Workshop on Spoken …, 2019 | 217 | 2019 |
Deep contextualized acoustic representations for semi-supervised speech recognition S Ling, Y Liu, J Salazar, K Kirchhoff ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 151 | 2020 |
Self-attention networks for connectionist temporal classification in speech recognition J Salazar, K Kirchhoff, Z Huang ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 146 | 2019 |
Align-Refine: Non-autoregressive speech recognition via iterative realignment EA Chi, J Salazar, K Kirchhoff Proceedings of the 2021 Conference of the North American Chapter of the …, 2021 | 52 | 2021 |
Don’t use English dev: On the zero-shot cross-lingual evaluation of contextual embeddings P Keung, Y Lu, J Salazar, V Bhardwaj Proceedings of the 2020 Conference on Empirical Methods in Natural Language …, 2020 | 37 | 2020 |
BERTphone: Phonetically-aware encoder representations for utterance-level speaker and language recognition S Ling, J Salazar, Y Liu, K Kirchhoff Proceedings of Speaker Odyssey 2020 (The Speaker and Language Recognition …, 2020 | 31 | 2020 |
Unsupervised bitext mining and translation via self-trained contextual embeddings P Keung, J Salazar, Y Lu, NA Smith Transactions of the Association for Computational Linguistics 8, 828-841, 2020 | 28 | 2020 |
Conway's subprime Fibonacci sequences RK Guy, T Khovanova, J Salazar Mathematics Magazine 87 (5), 323-337, 2014 | 14 | 2014 |
Attentional speech recognition models misbehave on out-of-domain utterances P Keung, W Niu, Y Lu, J Salazar, V Bhardwaj arXiv preprint arXiv:2002.05150, 2020 | 10 | 2020 |
Meta-learning the difference: Preparing large language models for efficient adaptation Z Hou, J Salazar, G Polovets Transactions of the Association for Computational Linguistics 10, 1249-1265, 2022 | 9 | 2022 |
Spoken question answering and speech continuation using spectrogram-powered LLM E Nachmani, A Levkovitch, R Hirsch, J Salazar, C Asawaroengchai, ... The Twelfth International Conference on Learning Representations, 2024 | 8* | 2024 |
Zero-shot end-to-end spoken language understanding via cross-modal selective self-training J He, J Salazar, K Yao, H Li, J Cai Proceedings of the 18th Conference of the European Chapter of the …, 2024 | 6 | 2024 |
Invariant representation learning for robust deep networks J Salazar, D Liang, Z Huang, ZC Lipton Workshop on Integration of Deep Learning Theories, NeurIPS 2018, 2018 | 5 | 2018 |
Multi-modal spoken language understanding systems A Gupta, J Salazar, P Zhang, K Kirchhoff, Y Zhang US Patent 11,562,735, 2023 | 3 | 2023 |
Crepant resolutions of Weierstrass models with torsion J Salazar Harvard University, 2017 | 2 | 2017 |
The representability hierarchy and Hilbert’s 13th problem J Salazar University of Chicago, Mathematics REU, 2016, 2016 | 1 | 2016 |
Model training system for custom speech-to-text models V Govindan, VS Varadarajan, CE Berkhoff, HM Joriwal, SM Bhavirisetty, ... US Patent 11,551,695, 2023 | | 2023 |
Persistent homology and the topology of motor cortical activity J Salazar, E West University of Chicago, Mathematics REU, 2016, 2016 | | 2016 |
Descent by 2-isogeny on elliptic curves: from Fermat to Weil J Salazar Harvard University, 2016 | | 2016 |