Automatic speech recognition using advanced deep learning approaches: A survey
Recent advancements in deep learning (DL) have posed a significant challenge for
automatic speech recognition (ASR). ASR relies on extensive training datasets, including …
automatic speech recognition (ASR). ASR relies on extensive training datasets, including …
Deep transfer learning for automatic speech recognition: Towards better generalization
Automatic speech recognition (ASR) has recently become an important challenge when
using deep learning (DL). It requires large-scale training datasets and high computational …
using deep learning (DL). It requires large-scale training datasets and high computational …
End-to-end neural systems for automatic children speech recognition: An empirical study
PG Shivakumar, S Narayanan - Computer Speech & Language, 2022 - Elsevier
A key desiderata for inclusive and accessible speech recognition technology is ensuring its
robust performance to children's speech. Notably, this includes the rapidly advancing neural …
robust performance to children's speech. Notably, this includes the rapidly advancing neural …
A wav2vec2-based experimental study on self-supervised learning methods to improve child speech recognition
Despite recent advancements in deep learning technologies, Child Speech Recognition
remains a challenging task. Current Automatic Speech Recognition (ASR) models require …
remains a challenging task. Current Automatic Speech Recognition (ASR) models require …
Audio augmentation for non-native children's speech recognition through discriminative learning
Automatic speech recognition (ASR) in children is a rapidly evolving field, as children
become more accustomed to interacting with virtual assistants, such as Amazon Echo …
become more accustomed to interacting with virtual assistants, such as Amazon Echo …
Comprehensive literature review on children automatic speech recognition system, acoustic linguistic mismatch approaches and challenges
Abstract Automatic Speech Recognition (ASR) system for children is as important as for
adults since children are more dependent on these systems nowadays, such as computer …
adults since children are more dependent on these systems nowadays, such as computer …
Using data augmentations and vtln to reduce bias in dutch end-to-end speech recognition systems
T Patel, O Scharenborg - arXiv preprint arXiv:2307.02009, 2023 - arxiv.org
Speech technology has improved greatly for norm speakers, ie, adult native speakers of a
language without speech impediments or strong accents. However, non-norm or diverse …
language without speech impediments or strong accents. However, non-norm or diverse …
End-to-end acoustic modelling for phone recognition of young readers
Automatic recognition systems for child speech are lagging behind those dedicated to adult
speech in the race of performance. This phenomenon is due to the high acoustic and …
speech in the race of performance. This phenomenon is due to the high acoustic and …
Exploring data augmentation in bias mitigation against non-native-accented speech
Automatic speech recognition (ASR) should serve every speaker, not only the majority
“standard” speakers of a language. In order to build inclusive ASR, mitigating the bias …
“standard” speakers of a language. In order to build inclusive ASR, mitigating the bias …
Analyzing and visualizing deep neural networks for speech recognition with saliency-adjusted neuron activation profiles
A Krug, M Ebrahimzadeh, J Alemann, J Johannsmeier… - Electronics, 2021 - mdpi.com
Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but
hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) …
hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) …