Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling J Cho, MK Baskar, R Li, M Wiesner, SH Mallidi, N Yalta, M Karafiat, ... 2018 IEEE Spoken Language Technology Workshop (SLT), 521-527, 2018 | 137 | 2018 |
Semi-supervised sequence-to-sequence ASR using unpaired speech and text MK Baskar, S Watanabe, R Astudillo, T Hori, L Burget, J Černocký arXiv preprint arXiv:1905.01152, 2019 | 68 | 2019 |
Speech enhancement using end-to-end speech recognition objectives AS Subramanian, X Wang, MK Baskar, S Watanabe, T Taniguchi, D Tran, ... 2019 IEEE Workshop on Applications of Signal Processing to Audio and …, 2019 | 63 | 2019 |
Transfer learning of language-independent end-to-end ASR with language model fusion H Inaguma, J Cho, MK Baskar, T Kawahara, S Watanabe ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 48 | 2019 |
BUT System for Low Resource Indian Language ASR. B Pulugundla, MK Baskar, S Kesiraju, E Egorova, M Karafiát, L Burget, ... Interspeech, 3182-3186, 2018 | 40 | 2018 |
Speaker adaptation for Wav2vec2 based dysarthric ASR MK Baskar, T Herzig, D Nguyen, M Diez, T Polzehl, L Burget, J Černocký arXiv preprint arXiv:2204.00770, 2022 | 28 | 2022 |
Multilingual blstm and speaker-specific vector adaptation in 2016 but babel system M Karafiát, MK Baskar, P Matějka, K Veselý, F Grézl, J Černocky 2016 IEEE Spoken Language Technology Workshop (SLT), 637-643, 2016 | 26 | 2016 |
Eat: Enhanced asr-tts for self-supervised speech recognition MK Baskar, L Burget, S Watanabe, RF Astudillo ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 23 | 2021 |
Analysis of multilingual blstm acoustic model on low and high resource languages M Karáfidt, MK Baskar, K Veselý, F Grézl, L Burget, J Černocký 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 21 | 2018 |
2016 BUT Babel System: Multilingual BLSTM Acoustic Model with i-Vector Based Adaptation. M Karafiát, MK Baskar, P Matejka, K Veselý, F Grezl, L Burget, J Cernocký INTERSPEECH, 719-723, 2017 | 20 | 2017 |
Promising accurate prefix boosting for sequence-to-sequence asr MK Baskar, L Burget, S Watanabe, M Karafiát, T Hori, JH Černocký ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 19 | 2019 |
Jan ˇCernocký,“ MK Baskar, S Watanabe, R Astudillo, T Hori, L Burget Semisupervised sequence-to-sequence asr using unpaired speech and text,” in …, 2019 | 18 | 2019 |
Residual memory networks: Feed-forward approach to learn long-term temporal dependencies MK Baskar, M Karafiát, L Burget, K Veselý, F Grézl, J Černocký 2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017 | 16 | 2017 |
Analysis of multilingual sequence-to-sequence speech recognition systems M Karafiát, MK Baskar, S Watanabe, T Hori, M Wiesner, J Černocký arXiv preprint arXiv:1811.03451, 2018 | 13 | 2018 |
Team ELISA System for DARPA LORELEI Speech Evaluation 2016. P Papadopoulos, R Travadi, C Vaz, N Malandrakis, U Hermjakob, ... INTERSPEECH, 2053-2057, 2017 | 9 | 2017 |
Language model integration based on memory control for sequence to sequence speech recognition J Cho, S Watanabe, T Hori, MK Baskar, H Inaguma, J Villalba, N Dehak ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 8 | 2019 |
DNNs for unsupervised extraction of pseudo speaker-normalized features without explicit adaptation data NM Joy, MK Baskar, S Umesh Speech Communication 92, 64-76, 2017 | 8 | 2017 |
Speaker adaptation of convolutional neural network using speaker specific subspace vectors of SGMM B Murali Karthick, P Kolhar, S Umesh Proc. Interspeech, 1096-1100, 2015 | 8 | 2015 |
Ask2Mask: Guided data selection for masked speech modeling MK Baskar, A Rosenberg, B Ramabhadran, Y Zhang, P Moreno IEEE Journal of Selected Topics in Signal Processing 16 (6), 1357-1366, 2022 | 7 | 2022 |
BUT Opensat 2019 speech recognition system M Karafiát, MK Baskar, I Szöke, HK Vydana, K Veselý, J Černocký arXiv preprint arXiv:2001.11360, 2020 | 7 | 2020 |