DARPA Speech Understanding Research: Difference between revisions
I.Marchenko (talk | contribs) |
I.Marchenko (talk | contribs) |
||
| Line 1: | Line 1: | ||
== Introduction == | == Introduction == | ||
DARPA stands for Defense Advanced Research Projects Agency, a research agency of the United States Department of Defense responsible for the development of emerging technologies for use by the military | DARPA stands for Defense Advanced Research Projects Agency, a research agency of the United States Department of Defense responsible for the development of emerging technologies for use by the military. As the DARPA's then-director George Heilemeir stated, "''Get computers to read Morse code in the presence of other code and noise, '''get computers to identify/detect key words in a stream of speech''', [...] make a real contribution to command and control, and; do a good thing in sonar"''<ref>Gaon, A. (2021). The Future of Copyright in the Age of Artificial Intelligence. Великобритания: Edward Elgar Publishing.</ref>. Thus, the main reason why it was the US Ministry of Defense who would fund such a project is that it could serve the navy's purposes. | ||
Considering that the project was to be used for military purposes, a number of requirements were put forward for it, especially relevant for military purposes. For example, the system had to be able to recognize several speakers at once, and also have no delay in recognition of speech. Thus, five main objectives of the research were established: | |||
{| class="wikitable" | {| class="wikitable" | ||
| | |Accepting connected speech | ||
|- | |- | ||
|From many cooperative speakers | |From many cooperative speakers | ||
| Line 16: | Line 14: | ||
|Real-time understanding | |Real-time understanding | ||
|} | |} | ||
This is the reason why it is ''understanding'' in the first place, and not ''recognition'': to attain successful understanding what was said or what was intented to be said rathern than simple recognizing some words taken out of context. | |||
== Historical Context == | |||
There had been partially successful attempts to understand discrete speech (see, for example, Bell's [[Bell Labs' Auditory Model|Audrey]]) but no system to understand speech that is continious existed at the time<ref>Funding a Revolution: Government Support for Computing Research. (1999). Украина: National Academies Press.</ref>. Moreover, previous methods dealt with vocabularies no larger than 200 words (e.g., IBM's 16-word "[[IBM Shoebox|Shoebox]]"), while DARPA's SUR aimed at a vocabulary with at least one thousand words. | |||
== Key Innovations == | == Key Innovations == | ||
- | - | ||
Revision as of 21:57, 15 September 2023
Introduction
DARPA stands for Defense Advanced Research Projects Agency, a research agency of the United States Department of Defense responsible for the development of emerging technologies for use by the military. As the DARPA's then-director George Heilemeir stated, "Get computers to read Morse code in the presence of other code and noise, get computers to identify/detect key words in a stream of speech, [...] make a real contribution to command and control, and; do a good thing in sonar"[1]. Thus, the main reason why it was the US Ministry of Defense who would fund such a project is that it could serve the navy's purposes.
Considering that the project was to be used for military purposes, a number of requirements were put forward for it, especially relevant for military purposes. For example, the system had to be able to recognize several speakers at once, and also have no delay in recognition of speech. Thus, five main objectives of the research were established:
| Accepting connected speech |
| From many cooperative speakers |
| Accepting 1000 words |
| Yielding only <10% semantic errors |
| Real-time understanding |
This is the reason why it is understanding in the first place, and not recognition: to attain successful understanding what was said or what was intented to be said rathern than simple recognizing some words taken out of context.
Historical Context
There had been partially successful attempts to understand discrete speech (see, for example, Bell's Audrey) but no system to understand speech that is continious existed at the time[2]. Moreover, previous methods dealt with vocabularies no larger than 200 words (e.g., IBM's 16-word "Shoebox"), while DARPA's SUR aimed at a vocabulary with at least one thousand words.
Key Innovations
-
Impact
-
Future research
-
References
To insert a reference, type <ref> and paste the source your exported from Zotero (or whatever reference manager you're using) in the pop up box which appears. Make sure links in citations are clickable using proper formatting. Once you do this, a footnote will appear.[3] and a reference comes at the end automatically. Please use this method to cite for Wiki articles only, not for your thesis.
- ↑ Gaon, A. (2021). The Future of Copyright in the Age of Artificial Intelligence. Великобритания: Edward Elgar Publishing.
- ↑ Funding a Revolution: Government Support for Computing Research. (1999). Украина: National Academies Press.
- ↑ Glantz, Richard "SHOEBOX: a personal file handling system for textual data." In Proceedings of the November 17-19, 1970, Fall Joint Computer Conference 1970. 535-545. [1]
Group members
- Igor Marchenko
- Wangyiyao Zhou
- Yanpei Ouyang
- Youyang Cai
- Yi Lei