model optimization
| Improvement of the performance of automatic speech recognition by the use of sound recordings collected while the service is in operation.
| |
| multi-word spotting
| A speech recognition system which is only interested in certain parts of each utterance: those parts containing application trigger words. In these systems, the utterances are modeled as out-of-vocabulary sequences (i.e. sequences which are to be rejected) and valid words (not to be rejected). The term multi-word spotting is used when the system can recognize more than one trigger word in the same utterance (e.g. multi-field information).
| |
|
