Language independent end-to-end architecture for joint language identification and speech recognition
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 …
developing ASR systems for new languages, by eliminating the need for linguistic …
Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling
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 …
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
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 …
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 …
higher requirements in terms of speech recognition accuracy. Low-resource speech …
Multilingual representations for low resource speech recognition and keyword search
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 …
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
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 …
developing ASR systems for new languages, by eliminating the need for linguistic …
Language-adversarial transfer learning for low-resource speech recognition
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 …
outperforms the model trained only by using the target language, especially under low …
Knowledge distillation across ensembles of multilingual models for low-resource languages
This paper investigates the effectiveness of knowledge distillation in the context of
multilingual models. We show that with knowledge distillation, Long Short-Term Memory …
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.
This paper presents the progress of acoustic models for lowresourced languages
(Assamese, Bengali, Haitian Creole, Lao, Zulu) developed within the second evaluation …
(Assamese, Bengali, Haitian Creole, Lao, Zulu) developed within the second evaluation …
Improving interpretability and regularization in deep learning
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 …
automatic speech recognition. However, the highly distributed representation in a deep …