Language independent end-to-end architecture for joint language identification and speech recognition

S Watanabe, T Hori, JR Hershey - 2017 IEEE Automatic Speech …, 2017 - ieeexplore.ieee.org
End-to-end automatic speech recognition (ASR) can significantly reduce the burden of
developing ASR systems for new languages, by eliminating the need for linguistic …

Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling

J Cho, MK Baskar, R Li, M Wiesner… - 2018 IEEE Spoken …, 2018 - ieeexplore.ieee.org
Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new
direction in speech research. The approach benefits by performing model training without …

Speech recognition and keyword spotting for low-resource languages: Babel project research at cued

MJF Gales, KM Knill, A Ragni… - … workshop on spoken …, 2014 - eprints.whiterose.ac.uk
Recently there has been increased interest in Automatic Speech Recognition (ASR) and
Key Word Spotting (KWS) systems for low resource languages. One of the driving forces for …

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 …

Multilingual representations for low resource speech recognition and keyword search

J Cui, B Kingsbury, B Ramabhadran… - 2015 IEEE workshop …, 2015 - ieeexplore.ieee.org
This paper examines the impact of multilingual (ML) acoustic representations on Automatic
Speech Recognition (ASR) and keyword search (KWS) for low resource languages in the …

An end-to-end language-tracking speech recognizer for mixed-language speech

H Seki, S Watanabe, T Hori, J Le Roux… - … on acoustics, speech …, 2018 - ieeexplore.ieee.org
End-to-end automatic speech recognition (ASR) can significantly reduce the burden of
developing ASR systems for new languages, by eliminating the need for linguistic …

Language-adversarial transfer learning for low-resource speech recognition

J Yi, J Tao, Z Wen, Y Bai - IEEE/ACM Transactions on Audio …, 2018 - ieeexplore.ieee.org
The acoustic model trained using the knowledge from the shared hidden layer (SHL) model
outperforms the model trained only by using the target language, especially under low …

Knowledge distillation across ensembles of multilingual models for low-resource languages

J Cui, B Kingsbury, B Ramabhadran… - … , Speech and Signal …, 2017 - ieeexplore.ieee.org
This paper investigates the effectiveness of knowledge distillation in the context of
multilingual models. We show that with knowledge distillation, Long Short-Term Memory …

[PDF][PDF] Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages.

Z Tüske, P Golik, D Nolden, R Schlüter, H Ney - Interspeech, 2014 - academia.edu
This paper presents the progress of acoustic models for lowresourced languages
(Assamese, Bengali, Haitian Creole, Lao, Zulu) developed within the second evaluation …

Improving interpretability and regularization in deep learning

C Wu, MJF Gales, A Ragni… - … /ACM Transactions on …, 2017 - ieeexplore.ieee.org
Deep learning approaches yield state-of-the-art performance in a range of tasks, including
automatic speech recognition. However, the highly distributed representation in a deep …