The Use of Deep Learning in Spoken Dialogue Systems
Duration: 46 mins 30 secs
Share this media item:
Embed this media item:
Embed this media item:
About this item
Description: | Keynote lecture by Professor Steve Young (University of Cambridge Dept. of Engineering/Siri Development Team) |
---|
Created: | 2017-12-06 15:53 |
---|---|
Collection: |
Cambridge Language Sciences
Language Sciences Annual Symposium 2017 - Language Sciences and Tech Innovation |
Publisher: | University of Cambridge |
Copyright: | J.A. Walsh |
Language: | eng (English) |
Distribution: | World (downloadable) |
Keywords: | deep learning; spoken dialogue systems; |
Explicit content: | No |
Aspect Ratio: | 4:3 |
Screencast: | No |
Bumper: | UCS Default |
Trailer: | UCS Default |
Abstract: | Spoken dialogue systems (SDS) provide the core enabling technology for building intelligent personal assistants. The function of an SDS is to understand each user input, decode the users intention or goal and then respond accordingly. Whereas historically much of this functionality has been provided by hand-crafted rule systems, modern systems increasingly rely on statistical models and machine learning. This talk will review the structure and components of a modern SDS and their implementation using deep neural networks. The provision of adequate quantities of annotated training data is a major limitation on progress and the talk will conclude by discussing ways in which this bottleneck might be eliminated. |
---|
Available Formats
Format | Quality | Bitrate | Size | |||
---|---|---|---|---|---|---|
MPEG-4 Video | 640x360 | 1.31 Mbits/sec | 458.25 MB | View | Download | |
WebM | 640x360 | 407.53 kbits/sec | 138.84 MB | View | Download | |
iPod Video | 480x360 | 483.97 kbits/sec | 164.83 MB | View | Download | |
MP3 | 44100 Hz | 249.76 kbits/sec | 85.16 MB | Listen | Download | |
Auto * | (Allows browser to choose a format it supports) |