Zobrazeno 1 - 10
of 587
pro vyhledávání: '"SEKHAR, P. CHANDRA"'
Training Memory-based transformers can require a large amount of memory and can be quite inefficient. We propose a novel two-phase training mechanism and a novel regularization technique to improve the training efficiency of memory-based transformers
Externí odkaz:
http://arxiv.org/abs/2311.08123
Autor:
Ojha, Rupam, Sekhar, C Chandra
Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different accent and var
Externí odkaz:
http://arxiv.org/abs/2108.02850
Distance Metric Learning (DML) seeks to learn a discriminative embedding where similar examples are closer, and dissimilar examples are apart. In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric using a f
Externí odkaz:
http://arxiv.org/abs/2105.05061
Autor:
Dawalatabad, Nauman, Sebastian, Jilt, Kuriakose, Jom, Sekhar, C. Chandra, Narayanan, Shrikanth, Murthy, Hema A.
Instrument separation in an ensemble is a challenging task. In this work, we address the problem of separating the percussive voices in the taniavartanam segments of Carnatic music. In taniavartanam, a number of percussive instruments play together o
Externí odkaz:
http://arxiv.org/abs/2103.03215
Publikováno v:
In e-Prime - Advances in Electrical Engineering, Electronics and Energy March 2024 7
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, 2021, pp 14-27
Speaker diarization is an important problem that is topical, and is especially useful as a preprocessor for conversational speech related applications. The objective of this paper is two-fold: (i) segment initialization by uniformly distributing spea
Externí odkaz:
http://arxiv.org/abs/2010.06304
Metric learning is an important problem in machine learning. It aims to group similar examples together. Existing state-of-the-art metric learning approaches require class labels to learn a metric. As obtaining class labels in all applications is not
Externí odkaz:
http://arxiv.org/abs/2008.09880
In this paper, we revamp the forgotten classical Semi-Supervised Distance Metric Learning (SSDML) problem from a Riemannian geometric lens, to leverage stochastic optimization within a end-to-end deep framework. The motivation comes from the fact tha
Externí odkaz:
http://arxiv.org/abs/2002.12394
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.