Spot keywords from very noisy and mixed speech

Autor:	Shi, Ying, Wang, Dong, Li, Lantian, Han, Jiqing, Yin, Shi
Rok vydání:	2023
Předmět:	Computer Science - Sound Computer Science - Artificial Intelligence Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Most existing keyword spotting research focuses on conditions with slight or moderate noise. In this paper, we try to tackle a more challenging task: detecting keywords buried under strong interfering speech (10 times higher than the keyword in amplitude), and even worse, mixed with other keywords. We propose a novel Mix Training (MT) strategy that encourages the model to discover low-energy keywords from noisy and mixed speech. Experiments were conducted with a vanilla CNN and two EfficientNet (B0/B2) architectures. The results evaluated with the Google Speech Command dataset demonstrated that the proposed mix training approach is highly effective and outperforms standard data augmentation and mixup training. Comment: Interspeech 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.17706 Zobrazit plný text záznamu View this record from Arxiv