ABSTRACT
In recent years, deep learning has predominantly changed the perspectives of varied fields in AI, including speech, vision, and NLP. In particular, the profound success of deep learning in a wide variety of domains has served as a benchmark for the many downstream applications in AI. Computer vision, voice, and NLP are three of the most popular application domains. Virtual assistants and smart speakers are examples of applications for computer vision, NLP, and speech recognition that are becoming more common in daily life. This chapter discusses the history, traditional machine learning algorithms, tools, techniques, and benchmark datasets which are extensively utilized in the fields of computer vision, NLP, and speech-processing fields.
