Human and machine hearing : extracting meaning from sound / Richard F. Lyon, Google, Inc.

By:

Lyon, Richard F [author.]

Material type: Text

TextPublication details: Cambridge, United Kingdom ; New York, NY, USA : Cambridge University Press, 2017.Description: xxi, 567 pages : illustrations (some color) ; 27 cmISBN:

9781107007536
1107007534

Subject(s):

DDC classification:

612.85 LYO

Contents:

Theories of hearing -- On logarithmic and power-law hearing -- Human hearing overview -- Acoustic approaches and auditory influence -- Introduction to linear systems -- Discrete-time and digital systems -- Resonators -- Gammatone and related filters -- Nonlinear systems -- Automatic gain control -- Waves in distributed systems -- Auditory filter models -- Modeling the cochlea -- The CARFAC digital cochlear model -- The cascade of asymmetric resonators -- The outer hair cell -- The inner hair cell -- The AGC loop filter -- Auditory nerve and cochlear nucleus -- The auditory image -- Binaural spatial hearing -- The auditory brain -- Neural networks for machine learning -- Feature spaces -- Sound search -- Musical melody matching -- Other applications.

Summary: If we understood more about how humans hear, we could make machines hear better, in the sense of being able to analyze sound and extract useful and meaningful information from it. Or so I claim. I have been working for decades, but more intensely in recent years, to add some substance to this claim, and to help engineers and scientists understand how the pieces fit together, so they can help move the art forward. There is still plenty to be done, and this book is my attempt to help focus the effort in this field into productive directions; to help new practitioners see enough of the evolution of ideas that they can skip to where new developments and experiments are needed, or to techniques that can already solve their sound understanding problems. The book-writing process has been tremendous fun, with support from family, friends, and colleagues. They do, however, have a tendency to ask two annoying questions: Is the book done yet? and Who is your audience? The first eventually answers itself, but I need to say a few words about the second. I find that interest in sound and hearing comes from people of many different disciplines, with complementary backgrounds and sometimes incompatible terminology and concepts. I want all of these people as my audience, as I want to teach a synthesis of their various viewpoints into a more comprehensive framework that includes everything needed to work on machine hearing problems. That is, electrical engineers, computer scientists, physicists, physiologists, audiologists, musicians, psychologists, and others are all part of my audience. Students, teachers, researchers, product managers, developers, and hackers are, too--Provided by publisher.

Holdings ( 1 )
Title notes ( 4 )

Holdings
Item type	Current library	Call number	Copy number	Status	Date due	Barcode
Standard Loan	Moylish Library Main Collection	612.85 LYO (Browse shelf(Opens below))	1	Available		39002100629162

Enhanced descriptions from Syndetics:

Human and Machine Hearing is the first book to comprehensively describe how human hearing works and how to build machines to analyze sounds in the same way that people do. Drawing on over thirty-five years of experience in analyzing hearing and building systems, Richard F. Lyon explains how we can now build machines with close-to-human abilities in speech, music, and other sound-understanding domains. He explains human hearing in terms of engineering concepts, and describes how to incorporate those concepts into machines for a wide range of modern applications. The details of this approach are presented at an accessible level, to bring a diverse range of readers, from neuroscience to engineering, to a common technical understanding. The description of hearing as signal-processing algorithms is supported by corresponding open-source code, for which the book serves as motivating documentation.

Includes bibliographical references (pages [497]-543) and indexes.

If we understood more about how humans hear, we could make machines hear better, in the sense of being able to analyze sound and extract useful and meaningful information from it. Or so I claim. I have been working for decades, but more intensely in recent years, to add some substance to this claim, and to help engineers and scientists understand how the pieces fit together, so they can help move the art forward. There is still plenty to be done, and this book is my attempt to help focus the effort in this field into productive directions; to help new practitioners see enough of the evolution of ideas that they can skip to where new developments and experiments are needed, or to techniques that can already solve their sound understanding problems. The book-writing process has been tremendous fun, with support from family, friends, and colleagues. They do, however, have a tendency to ask two annoying questions: Is the book done yet? and Who is your audience? The first eventually answers itself, but I need to say a few words about the second. I find that interest in sound and hearing comes from people of many different disciplines, with complementary backgrounds and sometimes incompatible terminology and concepts. I want all of these people as my audience, as I want to teach a synthesis of their various viewpoints into a more comprehensive framework that includes everything needed to work on machine hearing problems. That is, electrical engineers, computer scientists, physicists, physiologists, audiologists, musicians, psychologists, and others are all part of my audience. Students, teachers, researchers, product managers, developers, and hackers are, too--Provided by publisher.