Abstract Machine learning methods are extensively used for processing and analysing
speech signals by virtue of their performance gains over multiple domains. Deep learning …

Abstract Development of a native language robust ASR framework is very challenging as
well as an active area of research. Although an urge for investigation of effective front-end as …

Abstract One goal of Automatic Speech Recognition (ASR) is to convert the command of
human speech into computer-readable input, but noise interference is an important yet …

Contextual knowledge is of vital importance to end-to-end automatic speech recognition
(ASR) and spoken language understanding systems (SLU), especially for the long-tailed …

Malware detection is an increasingly important operational focus in cyber security,
particularly given the fast pace of such threats (eg, new malware variants introduced every …

With the rapid development of artificial intelligence technology, the impact of intelligent
interactive robots on human life is growing. This paper constructs an intelligent voice …

Computer vision systems are increasingly being deployed to real-world applications, such
as recognition models on autonomous vehicles, captioning models in presentation software …

Since its introduction, the Weighted Finite-State Transducers (WFSTs) networks, with their
precompiled search space in a single finite state, have provided an exceptional performance …

This Lecture• my personal interpretation (experience: 1978-2023):–unifying framework:
probabilistic models and Bayes decison theory–deep learning is just one out of many …