Search Results for author: Sameer Khurana

Found 11 papers, 2 papers with code

Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0

no code implementations7 Oct 2021 Sameer Khurana, Antoine Laurent, James Glass

We propose a simple and effective cross-lingual transfer learning method to adapt monolingual wav2vec-2. 0 models for Automatic Speech Recognition (ASR) in resource-scarce languages.

automatic-speech-recognition Cross-Lingual Transfer +2

Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training

no code implementations26 Nov 2020 Sameer Khurana, Niko Moritz, Takaaki Hori, Jonathan Le Roux

The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched.

automatic-speech-recognition Speech Recognition +1

A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning

no code implementations3 Jun 2020 Sameer Khurana, Antoine Laurent, Wei-Ning Hsu, Jan Chorowski, Adrian Lancucki, Ricard Marxer, James Glass

Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised learning approaches for linguistic representation learning from speech.

Latent Variable Models Representation Learning +2

DARTS: Dialectal Arabic Transcription System

no code implementations26 Sep 2019 Sameer Khurana, Ahmed Ali, James Glass

We analyze the following; transfer learning from high resource broadcast domain to low-resource dialectal domain and semi-supervised learning where we use in-domain unlabeled audio data collected from YouTube.

Language Modelling Transfer Learning

Multi-view Dimensionality Reduction for Dialect Identification of Arabic Broadcast Speech

no code implementations19 Sep 2016 Sameer Khurana, Ahmed Ali, Steve Renals

In this work, we present a new Vector Space Model (VSM) of speech utterances for the task of spoken dialect identification.

Dialect Identification Dimensionality Reduction

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