Search Results for author: Roman Bedyakin

Found 4 papers, 1 papers with code

Low-Resource Spoken Language Identification Using Self-Attentive Pooling and Deep 1D Time-Channel Separable Convolutions

no code implementations31 May 2021 Roman Bedyakin, Nikolay Mikhaylovskiy

In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results in low-resource setting for the language identification task and set up a SOTA for the Low Resource ASR challenge dataset.

Language Identification speech-recognition +2

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