Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Vaz, Colin"'
Autor:
Raju, Anirudh, Khare, Aparna, He, Di, Sklyar, Ilya, Chen, Long, Alptekin, Sam, Trinh, Viet Anh, Zhang, Zhe, Vaz, Colin, Ravichandran, Venkatesh, Maas, Roland, Rastrow, Ariya
Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being
Externí odkaz:
http://arxiv.org/abs/2401.08916
Autor:
Min, Do June, Stolcke, Andreas, Raju, Anirudh, Vaz, Colin, He, Di, Ravichandran, Venkatesh, Trinh, Viet Anh
Publikováno v:
Proc. IEEE ICASSP, June 2023
Current endpointing (EP) solutions learn in a supervised framework, which does not allow the model to incorporate feedback and improve in an online setting. Also, it is a common practice to utilize costly grid-search to find the best configuration fo
Externí odkaz:
http://arxiv.org/abs/2303.13407
Autor:
Lim, Yongwan, Toutios, Asterios, Bliesener, Yannick, Tian, Ye, Lingala, Sajan Goud, Vaz, Colin, Sorensen, Tanner, Oh, Miran, Harper, Sarah, Chen, Weiyi, Lee, Yoonjeong, Töger, Johannes, Montesserin, Mairym Lloréns, Smith, Caitlin, Godinez, Bianca, Goldstein, Louis, Byrd, Dani, Nayak, Krishna S., Narayanan, Shrikanth S.
Real-time magnetic resonance imaging (RT-MRI) of human speech production is enabling significant advances in speech science, linguistics, bio-inspired speech technology development, and clinical applications. Easy access to RT-MRI is however limited,
Externí odkaz:
http://arxiv.org/abs/2102.07896
We propose an algorithm to extract noise-robust acoustic features from noisy speech. We use Total Variability Modeling in combination with Non-negative Matrix Factorization (NMF) to learn a total variability subspace and adapt NMF dictionaries for ea
Externí odkaz:
http://arxiv.org/abs/1907.06859
Autor:
Vaz, Colin, Narayanan, Shrikanth
Publikováno v:
In Pattern Recognition Letters April 2021 144:105-111
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2016 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2016, p5735-5739, 5p
Publikováno v:
2014 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2014, p6275-6279, 5p
Publikováno v:
2014 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2014, p3306-3310, 5p
Autor:
Can D; Signal Analysis and Interpretation Lab, University of Southern California, CA 90089., Gibson J; Signal Analysis and Interpretation Lab, University of Southern California, CA 90089., Vaz C; Signal Analysis and Interpretation Lab, University of Southern California, CA 90089., Georgiou PG; Signal Analysis and Interpretation Lab, University of Southern California, CA 90089., Narayanan SS; Signal Analysis and Interpretation Lab, University of Southern California, CA 90089.
Publikováno v:
Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference) [Proc IEEE Int Conf Acoust Speech Signal Process] 2014 May; Vol. 2014, pp. 3306-3310.