The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2021 The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research.
Xian Shi +7 more
semanticscholar +1 more source
MixSpeech: Data Augmentation for Low-Resource Automatic Speech Recognition [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2021 In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features (e.g., mel ...
Linghui Meng +5 more
semanticscholar +1 more source
Automatic Speech Recognition (ASR) Systems for Children: A Systematic Literature Review
Applied Sciences, 2022 Automatic speech recognition (ASR) is one of the ways used to transform acoustic speech signals into text. Over the last few decades, an enormous amount of research work has been done in the research area of speech recognition (SR). However, most studies
Vivek Bhardwaj +9 more
semanticscholar +1 more source
Multi-Task Self-Supervised Learning for Robust Speech Recognition [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020 Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a ...
M. Ravanelli +6 more
semanticscholar +1 more source
An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition [PDF]
Automatic Speech Recognition & Understanding, 2021 Self-supervised pretraining on speech data has achieved a lot of progress. High-fidelity representation of the speech signal is learned from a lot of untranscribed data and shows promising performance.
Xuankai Chang +10 more
semanticscholar +1 more source
CHiME-6 Challenge: Tackling Multispeaker Speech Recognition for Unsegmented Recordings [PDF]
6th International Workshop on Speech Processing in Everyday Environments (CHiME 2020), 2020 Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6).
Shinji Watanabe +3 more
semanticscholar +1 more source
Improved Noisy Student Training for Automatic Speech Recognition [PDF]
Interspeech, 2020 Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly.
Daniel S. Park +7 more
semanticscholar +1 more source
Emotional Interactive Simulation System of English Speech Recognition in Virtual Context
Complexity, 2020 With the development of virtual scenes, the degree of simulation and functions of virtual reality have been very complete, providing a new platform and perspective for teaching design.
Dan Li
doaj +1 more source
Effect of Time-domain Windowing on Isolated Speech Recognition System Performance [PDF]
International Journal of Electronics and Telecommunications, 2022 Speech recognition system extract the textual data from the speech signal. The research in speech recognition domain is challenging due to the large variabilities involved with the speech signal.
Ananthakrishna Thalengala +2 more
doaj +1 more source
Research Status and Prospect of Transformer in Speech Recognition
Jisuanji kexue yu tansuo, 2021 As a new deep learning algorithm framework, Transformer has attracted more and more researchers?? attention and has become a current research hotspot. Inspired by humans focusing on important things only, the self-attention mechanism in the Transformer ...
ZHANG Xiaoxu, MA Zhiqiang, LIU Zhiqiang, ZHU Fangyuan, WANG Chunyu
doaj +1 more source