Search Results for author: Jahangir Alam

Found 7 papers, 1 papers with code

Attentive activation function for improving end-to-end spoofing countermeasure systems

no code implementations3 May 2022 Woo Hyun Kang, Jahangir Alam, Abderrahim Fathan

The main objective of the spoofing countermeasure system is to detect the artifacts within the input speech caused by the speech synthesis or voice conversion process.

Speech Synthesis Voice Conversion

Robust Speech Representation Learning via Flow-based Embedding Regularization

no code implementations7 Dec 2021 Woo Hyun Kang, Jahangir Alam, Abderrahim Fathan

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals.

Language Identification Representation Learning +1

Learning Semantic Similarities for Prototypical Classifiers

no code implementations1 Jan 2021 Joao Monteiro, Isabela Albuquerque, Jahangir Alam, Tiago Falk

Recent metric learning approaches parametrize semantic similarity measures through the use of an encoder trained along with a similarity model, which operates over pairs of representations.

Few-Shot Learning Metric Learning +4

An end-to-end approach for the verification problem: learning the right distance

1 code implementation ICML 2020 Joao Monteiro, Isabela Albuquerque, Jahangir Alam, R. Devon Hjelm, Tiago Falk

In this contribution, we augment the metric learning setting by introducing a parametric pseudo-distance, trained jointly with the encoder.

Metric Learning

Adapting End-to-End Neural Speaker Verification to New Languages and Recording Conditions with Adversarial Training

no code implementations7 Nov 2018 Gautam Bhattacharya, Jahangir Alam, Patrick Kenny

In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks.

Text-Independent Speaker Verification

Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-End Speaker Verification

no code implementations7 Nov 2018 Gautam Bhattacharya, Joao Monteiro, Jahangir Alam, Patrick Kenny

Furthermore, we are able to significantly boost verification performance by averaging our different GAN models at the score level, achieving a relative improvement of 7. 2% over the baseline.

Dimensionality Reduction Speaker Verification

Cannot find the paper you are looking for? You can Submit a new open access paper.