Towards efficient recurrent architectures: a deep LSTM neural network applied to speech enhancement and recognition

• Main Authors: Wang, Jing, Saleem, Nasir, Gunawan, Teddy Surya
• Format: Article
• Language: English; English; English
• Published: Springer Nature 2024
• Subjects: TK7885 Computer engineering
• Online Access: http://irep.iium.edu.my/112153/1/112153_Towards%20efficient%20recurrent%20architectures.pdf; http://irep.iium.edu.my/112153/2/112153_Towards%20efficient%20recurrent%20architectures_SCOPUS.pdf; http://irep.iium.edu.my/112153/3/112153_Towards%20efficient%20recurrent%20architectures_WOS.pdf; http://irep.iium.edu.my/112153/; https://link.springer.com/article/10.1007/s12559-024-10288-y

Long short-term memory (LSTM) has proven effective in modeling sequential data. However, it may encounter challenges in accurately capturing long-term temporal dependencies. LSTM plays a central role in speech enhancement by effectively modeling and capturing temporal dependencies in speech signals....