Command Recognition
Command recognition research focuses on accurately identifying spoken or gestural commands from various sources, aiming to improve efficiency and safety across diverse applications. Current efforts concentrate on enhancing model robustness in noisy environments using techniques like convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid architectures incorporating tensor-train networks, often optimized through algorithms such as differential evolution. These advancements are crucial for improving human-computer interaction in areas like aviation, in-vehicle systems, and assistive technologies, particularly for low-resource languages and individuals with speech impairments.
Papers
CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition
Wenliang Dai, Samuel Cahyawijaya, Tiezheng Yu, Elham J. Barezi, Peng Xu, Cheuk Tung Shadow Yiu, Rita Frieske, Holy Lovenia, Genta Indra Winata, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, Pascale Fung
Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognition
Jun Qi, Javier Tejedor