22 citations · 44 across the 9 of their papers we have counts for
9 papers
Memory-efficient Stochastic methods for Memory-based Transformers
Vishwajit Kumar Vishnu, C. Chandra Sekhar
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 tec…
Unsupervised Domain Adaptation in Speech Recognition using Phonetic Features
Rupam Ojha, C Chandra Sekhar
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 m…
Semi-Supervised Metric Learning: A Deep Resurrection
Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar
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…
Front-end Diarization for Percussion Separation in Taniavartanam of Carnatic Music Concerts
Nauman Dawalatabad, Jilt Sebastian, Jom Kuriakose +3
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…
Novel Architectures for Unsupervised Information Bottleneck based Speaker Diarization of Meetings
Nauman Dawalatabad, Srikanth Madikeri, C. Chandra Sekhar +1
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…
Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss
Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar
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 t…
Affinity guided Geometric Semi-Supervised Metric Learning
Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar
In this paper, we revamp the forgotten classical Semi-Supervised Distance Metric Learning (SSDML) problem from a Riemannian geometric lens, to leverage stochastic optimization with…
A Probabilistic approach for Learning Embeddings without Supervision
Ujjal Kr Dutta, Mehrtash Harandi, Chandra Sekhar Chellu
For challenging machine learning problems such as zero-shot learning and fine-grained categorization, embedding learning is the machinery of choice because of its ability to learn…
Incremental Transfer Learning in Two-pass Information Bottleneck based Speaker Diarization System for Meetings
Nauman Dawalatabad, Srikanth Madikeri, C Chandra Sekhar +1
The two-pass information bottleneck (TPIB) based speaker diarization system operates independently on different conversational recordings. TPIB system does not consider previously…