5 Books we read
from machine learning to speech analytics
The applications of artificial intelligence are the talk of the day, as they are used to solve a whole range of intractable problems. The influx of new technologies has disrupted many industries and created many opportunities for a new generation of engineers and data analysts. However, still today, only 20 percent of those organizations aware of AI, actually use it. The main reason? Many executives are still wondering, “What can AI do for my business? As a matter of fact, machine learning holds a great promise in the field of business predictive analytics for providing decision-makers with information, helping companies solve long-standing problems in new ways.
To help you gauge the emerging role of AI in the speech analytics, our engineer and analyst team compiled a few book recommendations. Take a deep breath and dive in!
Great books help you understand, and they help you feel understood.
– John Green
1. SPEECH AND LANGUAGE PROCESSING: INTERNATIONAL EDITION
by Daniel Jurafsky (Author), James H. Martin (Author)
Our first book recommendation is suitable for those taking undergraduate or advanced undergraduate courses in Natural Language Processing, Speech Recognition, Computational Linguistics, and Human Language Processing. For one thing, this book is the first of its kind to thoroughly cover language technology. It takes an empirical approach to the subject, based on applying statistical and other machine-learning algorithms to large corporations. In addition. the authors cover areas that traditionally are taught in different courses, to describe a unified vision of speech and language processing.
2. DEEP LEARNING
by Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press, 2016
The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular.
3. PATTERN RECOGNITION AND MACHINE LEARNING
by Christopher M. Bishop
Our third recommendation refers to the first textbook on pattern recognition to present the Bayesian viewpoint. In particular, the book presents approximate inference algorithms that permit fast approximate answers in situations where exact answers are not feasible. Students in machine learning, statistics, computer science, signal processing, computer vision, data mining, and bioinformatics will find this book particularly helpful.
4. MACHINE LEARNING: A BAYESIAN AND OPTIMIZATION PERSPECTIVE
by Sergios Theodoridis
The book presents the major machine learning methods as they have been developed in different disciplines, such as statistics, statistical and adaptive signal processing and computer science. Moreover, the reader can find a unifying perspective on machine learning covering both probabilistic and deterministic approaches together with the Bayesian inference approach.
5. THEORY AND APPLICATIONS OF DIGITAL SPEECH PROCESSING
by Lawrence Rabiner and Ronald Schafer
This is an ideal book for graduate students in digital signal processing, and undergraduate students in Electrical and Computer Engineering.
Intrigued yet? For more information on how we measure the how and why in conversational data with artificial intelligence and deep learning, please refer to our Whitepaper On Behavioral Signal Processing.
This post was originally published on Behavioral Signals website and includes books our tech team suggested.
***Did you know that we have a bi-monthly newsletter with the latest news
and trends in Voice and Emotion AI? Sign Up here
