Despite rapid progress in the recent past, current speech recognition systems still require
labeled training data which limits this technology to a small fraction of the languages spoken …

We employ a combination of recent developments in semi-supervised learning for automatic
speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled …

Abstract Time Delay Neural Networks (TDNNs), also known as onedimensional
Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural …

In this paper, we present TED-LIUM release 3 corpus (TED-LIUM 3 is available on
https://lium. univ-lemans. fr/ted-lium3/) dedicated to speech recognition in English, which …

Unsupervised speech recognition has shown great potential to make Automatic Speech
Recognition (ASR) systems accessible to every language. However, existing methods still …

Automatic speech recognition (ASR) systems promise to deliver objective interpretation of
human speech. Practice and recent evidence suggests that the state-of-the-art (SotA) ASRs …

Practice and recent evidence show that state-of-the-art (SotA) automatic speech recognition
(ASR) systems do not perform equally well for all speaker groups. Many factors can cause …

Lattice-rescoring is a common approach to take advantage of recurrent neural language
models in ASR, where a word-lattice is generated from 1st-pass decoding and the lattice is …

In this paper, we propose a novel teacher-student learning framework for the preprocessing
of a speech recognizer, leveraging the online noise tracking capabilities of improved minima …

This paper describes the current TTÜ speech transcription system for Estonian speech. The
system is designed to handle semi-spontaneous speech, such as broadcast conversations …