Automatic speech recognition: Systematic literature review

S Alharbi, M Alrazgan, A Alrashed, T Alnomasi… - Ieee …, 2021 - ieeexplore.ieee.org
A huge amount of research has been done in the field of speech signal processing in recent
years. In particular, there has been increasing interest in the automatic speech recognition …

Smart home personal assistants: a security and privacy review

JS Edu, JM Such, G Suarez-Tangil - ACM Computing Surveys (CSUR), 2020 - dl.acm.org
Smart Home Personal Assistants (SPA) are an emerging innovation that is changing the
means by which home users interact with technology. However, several elements expose …

Continuous speech separation with conformer

S Chen, Y Wu, Z Chen, J Wu, J Li… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
Continuous speech separation was recently proposed to deal with the overlapped speech in
natural conversations. While it was shown to significantly improve the speech recognition …

Adaptation algorithms for neural network-based speech recognition: An overview

P Bell, J Fainberg, O Klejch, J Li… - IEEE Open Journal …, 2020 - ieeexplore.ieee.org
We present a structured overview of adaptation algorithms for neural network-based speech
recognition, considering both hybrid hidden Markov model/neural network systems and end …

gpuRIR: A python library for room impulse response simulation with GPU acceleration

D Diaz-Guerra, A Miguel, JR Beltran - Multimedia Tools and Applications, 2021 - Springer
Abstract The Image Source Method (ISM) is one of the most employed techniques to
calculate acoustic Room Impulse Responses (RIRs), however, its computational complexity …

Conditional teacher-student learning

Z Meng, J Li, Y Zhao, Y Gong - ICASSP 2019-2019 IEEE …, 2019 - ieeexplore.ieee.org
The teacher-student (T/S) learning has been shown to be effective for a variety of problems
such as domain adaptation and model compression. One shortcoming of the T/S learning is …

Efficient knowledge distillation for rnn-transducer models

S Panchapagesan, DS Park, CC Chiu… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
Knowledge Distillation is an effective method of transferring knowledge from a large model
to a smaller model. Distillation can be viewed as a type of model compression, and has …

[HTML][HTML] Bioinspired dual-channel speech recognition using graphene-based electromyographic and mechanical sensors

H Tian, X Li, Y Wei, S Ji, Q Yang, GY Gou… - Cell Reports Physical …, 2022 - cell.com
Automatic speech recognition (ASR) is helpful to improve quality of life. However, the
performance of ASR degrades in the case of noisy environment, limited privacy, and speech …

Frequency domain multi-channel acoustic modeling for distant speech recognition

W Minhua, K Kumatani, S Sundaram… - ICASSP 2019-2019 …, 2019 - ieeexplore.ieee.org
Conventional far-field automatic speech recognition (ASR) systems typically employ
microphone array techniques for speech enhancement in order to improve robustness …

Multi-view teacher–student network

Y Tian, S Sun, J Tang - Neural Networks, 2022 - Elsevier
Multi-view learning aims to fully exploit the view-consistency and view-discrepancy for
performance improvement. Knowledge Distillation (KD), characterized by the so-called …