The third 'CHiME'speech separation and recognition challenge: Dataset, task and baselines

J Barker, R Marxer, E Vincent… - 2015 IEEE Workshop on …, 2015 - ieeexplore.ieee.org
The CHiME challenge series aims to advance far field speech recognition technology by
promoting research at the interface of signal processing and automatic speech recognition …

An analysis of environment, microphone and data simulation mismatches in robust speech recognition

E Vincent, S Watanabe, AA Nugraha, J Barker… - Computer Speech & …, 2017 - Elsevier
Speech enhancement and automatic speech recognition (ASR) are most often evaluated in
matched (or multi-condition) settings where the acoustic conditions of the training data …

The third 'CHiME'speech separation and recognition challenge: Analysis and outcomes

J Barker, R Marxer, E Vincent, S Watanabe - Computer Speech & …, 2017 - Elsevier
This paper presents the design and outcomes of the CHiME-3 challenge, the first open
speech recognition evaluation designed to target the increasingly relevant multichannel …

A curriculum learning method for improved noise robustness in automatic speech recognition

S Braun, D Neil, SC Liu - 2017 25th European Signal …, 2017 - ieeexplore.ieee.org
The performance of automatic speech recognition systems under noisy environments still
leaves room for improvement. Speech enhancement or feature enhancement techniques for …

The CHiME challenges: Robust speech recognition in everyday environments

JP Barker, R Marxer, E Vincent, S Watanabe - New era for robust speech …, 2017 - Springer
The CHiME challenge series has been aiming to advance the development of robust
automatic speech recognition for use in everyday environments by encouraging research at …

Multi-style learning with denoising autoencoders for acoustic modeling in the internet of things (IoT)

P Lin, DC Lyu, F Chen, SS Wang, Y Tsao - Computer Speech & Language, 2017 - Elsevier
We propose a multi-style learning (multi-style training+ deep learning) procedure that relies
on deep denoising autoencoders (DAEs) to extract and organize the most discriminative …

Sequence-level confidence classifier for asr utterance accuracy and application to acoustic models

A Afshan, K Kumar, J Wu - arxiv preprint arxiv:2107.00099, 2021 - arxiv.org
Scores from traditional confidence classifiers (CCs) in automatic speech recognition (ASR)
systems lack universal interpretation and vary with updates to the underlying confidence or …

RETRACTED ARTICLE: Advancing an in-memory computing for a multi-accent real-time voice frequency recognition modeling: a comprehensive study of models & …

U Tariq, A Aldaej - Multimedia Tools and Applications, 2020 - Springer
In this age of pervasive computing, numerous scientific accomplishments, such as artificial
intelligence and machine learning [ML], have conveyed exciting uprisings to human …

Deep speech extraction with time-varying spatial filtering guided by desired direction attractor

Y Nakagome, M Togami, T Ogawa… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
In this investigation, a deep neural network (DNN) based speech extraction method is
proposed to enhance a speech signal propagating from the desired direction. The proposed …

Robust utterance classification using multiple classifiers in the presence of speech recognition errors

T Homma, K Shima, T Matsumoto - 2016 IEEE Spoken …, 2016 - ieeexplore.ieee.org
In order to achieve an utterance classifier that not only works robustly against speech
recognition errors but also maintains high accuracy for input with no errors, we propose the …