ASR-complete
From Wikipedia, the free encyclopedia
ASR-complete is, by analogy to NP-completeness in complexity theory, a term to indicate that the difficulty of a computational problem is equivalent to solving the central Automatic Speech Recognition problem, i.e. recognize and understanding spoken language. Note that unlike NP-completeness, this term is typically used more informally.
Such problems are hypothesised to include:
- Spoken natural language understanding
- Understanding speech from far-field microphones - i.e. handling the reverbation and background noise
These problems are easy for humans to do (in fact, they are described directly in terms of imitating humans). Some systems can solve very simple restricted versions of these problems, but none can solve them in their full generality.
[edit] See also
[edit] External links
[edit] Reference
- Nelson Morgan et al, MEETINGS ABOUT MEETINGS: RESEARCH AT ICSI ON SPEECH IN MULTIPARTY CONVERSATIONS, In: ICASSP 2003, April 6-10, 2003.
