Atjaunināt sīkdatņu piekrišanu

Hey Cyba: The Inner Workings of a Virtual Personal Assistant [Mīkstie vāki]

3.50/5 (3 ratings by Goodreads)
(University of Cambridge)
  • Formāts: Paperback / softback, 254 pages, height x width x depth: 228x153x16 mm, weight: 390 g, Worked examples or Exercises
  • Izdošanas datums: 08-Apr-2021
  • Izdevniecība: Cambridge University Press
  • ISBN-10: 1108972365
  • ISBN-13: 9781108972369
Citas grāmatas par šo tēmu:
  • Mīkstie vāki
  • Cena: 28,70 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
Hey Cyba: The Inner Workings of a Virtual Personal AssistantPalielināt
  • Formāts: Paperback / softback, 254 pages, height x width x depth: 228x153x16 mm, weight: 390 g, Worked examples or Exercises
  • Izdošanas datums: 08-Apr-2021
  • Izdevniecība: Cambridge University Press
  • ISBN-10: 1108972365
  • ISBN-13: 9781108972369
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9781108972369.html
Keywords:
Recent developments in artificial intelligence, especially neural network and deep learning technology, have led to rapidly improving performance in voice assistants such as Siri and Alexa. Over the next few years, capability will continue to improve and become increasingly personalised. Today's voice assistants will evolve into virtual personal assistants firmly embedded within our everyday lives. Told through the view of a fictitious personal assistant called Cyba, this book provides an accessible but detailed overview of how a conversational voice assistant works, especially how it understands spoken language, manages conversations, answers questions and generates responses. Cyba explains through examples and diagrams the neural network technology underlying speech recognition and synthesis, natural language understanding, knowledge representation, conversation management, language translation and chatbot technology. Cyba also explores the implications of this rapidly evolving technology for security, privacy and bias, and gives a glimpse of future developments. Cyba's website can be found at HeyCyba.com.

Recenzijas

'Hey Cyba is based on the author's long history of research and his rich experiences of developing various voice assistant systems. With the current rapid progress and wide deployment of AI-based voice assistant systems all over the world, the publication is very timely, and the book has a very unique and interesting writing style. I strongly recommend it to anyone interested in this area.' Sadaoki Furui, Toyota Technological Institute at Chicago 'Hey Cyba, written by one of the giants in the field of man machine interfaces, provides an in depth guide to the workings and future of conversational personal assistants. Written in the first person style of the computer itself this is a highly engaging, informative and authoritative read.' Hermann Hauser, Amadeus Capital Partners 'The book to introduce the technology behind our voice assistants to everyone. Voice assistants are among the most complex AI/ML (artificial intelligence/machine learning) systems. Hey, Cyba manages to present this complex AI/ML system in one easy-to-read narrative covering each aspect of the voice assistant in just the right depth. I wonder whether there is anyone but Steve with the deep knowledge and academic and industry experience required to write such a book.' Björn Hoffmeister, Director of Machine Learning at Amazon/Alexa 'This enjoyable text deftly illuminates the technology behind a common experience Highly recommended.' M. Mounts, Choice Connect

Papildus informācija

Reveals how AI works and provides insight into what we can expect of it now and in the future.
Preface ix
1 May I Introduce Myself?
1(12)
1.1 What Does a Virtual Personal Assistant Do?
2(1)
1.2 Some Background History
3(3)
1.3 My Place of Work
6(2)
1.4 Privacy and Trust
8(1)
1.5 My Goal in Life
9(2)
1.6 How Smart Am I?
11(2)
2 My Inner Workings
13(7)
2.1 Anatomy of a Conversation
13(4)
2.2 My Working Parts
17(3)
3 How My Brain Works
20(26)
3.1 Patterns
21(2)
3.2 Artificial Neural Networks
23(3)
3.3 Recognising Patterns
26(4)
3.4 Training a Neural Network
30(2)
3.5 From Static Patterns to Sequences
32(6)
3.6 Convolutional Networks
38(2)
3.7 Scaling-up
40(6)
4 Knowing What I Know
46(16)
4.1 My Knowledge Graph
47(2)
4.2 Nodes and Links
49(3)
4.3 Intent Graphs and Queries
52(4)
4.4 Creating and Updating Entities
56(6)
5 What Did You Say?
62(20)
5.1 Human Speech Production
62(2)
5.2 My Artificial Ears
64(2)
5.3 Why Is Speech Recognition So Hard?
66(2)
5.4 Capturing the Audio
68(4)
5.5 From Sounds to Words
72(3)
5.6 Pay Attention!
75(3)
5.7 Adding a Language Model
78(2)
5.8 A Postscript from the Bard
80(2)
6 What Does That Mean?
82(22)
6.1 Intent Graph Generation and Ranking
83(7)
6.2 Entity Linking
90(3)
6.3 Multi-task Classification Using a Shared Encoder
93(1)
6.4 Character-Based Word Embedding
94(3)
6.5 Sentence Encoding and Recognition
97(2)
6.6 Sentence/Intent Graph Matching
99(2)
6.7 Candidate Ranking
101(3)
7 What Should I Say Next?
104(17)
7.1 My Conversation Manager
105(4)
7.2 Learning a Good Dialogue Policy
109(3)
7.3 Conversational Memory
112(1)
7.4 Generating My Response
113(8)
8 Listen To Me
121(15)
8.1 From Text to Speech
121(3)
8.2 Text Processing
124(1)
8.3 Neural Speech Synthesis
125(2)
8.4 Setting the Right Tone
127(4)
8.5 Generating the Waveform
131(5)
9 How Do You Say That In ...?
136(16)
9.1 Transformer Networks
138(4)
9.2 Using a Transformer Network for Language Translation
142(2)
9.3 Characters or Words or
144(3)
9.4 Multi-lingual Translation
147(1)
9.5 Beam Search
148(1)
9.6 The Limits of Neural Machine Translation
149(3)
10 Let's Chat
152(13)
10.1 My Chatty Responders
155(1)
10.2 Hand-Crafted Response Generation
156(1)
10.3 Retrieval-Based Response Generation
157(2)
10.4 Web-Search Response Generation
159(1)
10.5 Encoder-Decoder Response Generation
160(3)
10.6 Selecting the Best Response
163(1)
10.7 Social Chatbots
163(2)
11 Can You Trust Me?
165(18)
11.1 Security
166(2)
11.2 Privacy
168(5)
11.3 Bias
173(4)
11.4 Transparency
177(3)
11.5 Safety
180(1)
11.6 Personality
180(2)
11.7 The Bottom Line
182(1)
12 When All Is Quiet
183(12)
12.1 Knowledge Graph Maintenance
184(5)
12.2 Federated Learning
189(2)
12.3 Student--Teacher Model Reduction
191(3)
12.4 End of the Tour
194(1)
13 Future Upgrades And Beyond
195(16)
13.1 Personalisation
197(1)
13.2 Towards Self-Learning
198(2)
13.3 The Neural--Symbolic Interface
200(2)
13.4 Commonsense Reasoning and Inference
202(2)
13.5 Planning
204(2)
13.6 Super-intelligence?
206(3)
13.7 Another Day
209(2)
Glossary 211(10)
Notes 221(10)
Index 231
Steve Young has more than 40 years of research experience in speech processing and AI. He founded a number of speech technology startups including Entropic acquired by Microsoft in 1999 and VocalIQ acquired by Apple in 2015, following which he worked in the Apple Siri Development team. He is a Fellow of the Royal Society, the Royal Academy of Engineering, the IET and the IEEE. He holds an IEEE Signal Processing Society Technical Achievement Award, the ISCA Medal for Scientific Achievement, a European Signal Processing Society Technical Achievement Award and the IEEE James L. Flanagan Speech and Audio Processing Award.