End-to-end speech recognition: A survey
In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …
learning has brought considerable reductions in word error rate of more than 50% relative …
Deep learning: methods and applications
This monograph provides an overview of general deep learning methodology and its
applications to a variety of signal and information processing tasks. The application areas …
applications to a variety of signal and information processing tasks. The application areas …
[HTML][HTML] Frontier Research on Low-Resource Speech Recognition Technology
W Slam, Y Li, N Urouvas - Sensors, 2023 - mdpi.com
With the development of continuous speech recognition technology, users have put forward
higher requirements in terms of speech recognition accuracy. Low-resource speech …
higher requirements in terms of speech recognition accuracy. Low-resource speech …
Foundations and trends in signal processing: Deep learning–methods and applications
This monograph provides an overview of general deep learning methodology and its
applications to a variety of signal and information processing tasks. The application areas …
applications to a variety of signal and information processing tasks. The application areas …
Multi-accent speech recognition with hierarchical grapheme based models
We train grapheme-based acoustic models for speech recognition using a hierarchical
recurrent neural network architecture with connectionist temporal classification (CTC) loss …
recurrent neural network architecture with connectionist temporal classification (CTC) loss …
Computer multimedia assisted language and literature teaching using Heuristic hidden Markov model and statistical language model
J Zhang, C Wang, A Muthu, VM Varatharaju - Computers & Electrical …, 2022 - Elsevier
Computer technology has been used for decades in secondary education and foreign
language preparation. Still, attempts to incorporate technology have presented educators …
language preparation. Still, attempts to incorporate technology have presented educators …
No need for a lexicon? evaluating the value of the pronunciation lexica in end-to-end models
TN Sainath, R Prabhavalkar, S Kumar… - … , Speech and Signal …, 2018 - ieeexplore.ieee.org
For decades, context-dependent phonemes have been the dominant sub-word unit for
conventional acoustic modeling systems. This status quo has begun to be challenged …
conventional acoustic modeling systems. This status quo has begun to be challenged …
Diacritic recognition performance in arabic asr
H Aldarmaki, A Ghannam - arXiv preprint arXiv:2302.14022, 2023 - arxiv.org
We present an analysis of diacritic recognition performance in Arabic Automatic Speech
Recognition (ASR) systems. As most existing Arabic speech corpora do not contain all …
Recognition (ASR) systems. As most existing Arabic speech corpora do not contain all …
Improved Arabic speech recognition system through the automatic generation of fine-grained phonetic transcriptions
E Alsharhan, A Ramsay - Information Processing & Management, 2019 - Elsevier
This paper aims at determining the best way to exploit the phonological properties of the
Arabic language in order to improve the performance of the speech recognition system. One …
Arabic language in order to improve the performance of the speech recognition system. One …
Acoustic data-driven pronunciation lexicon for large vocabulary speech recognition
Speech recognition systems normally use handcrafted pronunciation lexicons designed by
linguistic experts. Building and maintaining such a lexicon is expensive and time …
linguistic experts. Building and maintaining such a lexicon is expensive and time …