Abstract
Speech-to-text, or spoken language recognition technology has been under
development for a long time. Now when the computers have become more
powerful, processing speed has increased and other physical obstacles are no
longer limiting the implementation, this technology can be developed and
utilized increasingly. The fields which it could be applied to are numerous.
Information channels are also increasing rapidly and the enormous
information flow is not easy to control. Utilizing speech-to-text technology it
is possible to automatically transcribe news content, create indexing for it and
make the multimedia presentation searchable the same way a normal text can
be searched. How far have we come? Does a usable technology exist, and how good is it? Well, there is no way of telling unless it is tested.
development for a long time. Now when the computers have become more
powerful, processing speed has increased and other physical obstacles are no
longer limiting the implementation, this technology can be developed and
utilized increasingly. The fields which it could be applied to are numerous.
Information channels are also increasing rapidly and the enormous
information flow is not easy to control. Utilizing speech-to-text technology it
is possible to automatically transcribe news content, create indexing for it and
make the multimedia presentation searchable the same way a normal text can
be searched. How far have we come? Does a usable technology exist, and how good is it? Well, there is no way of telling unless it is tested.
| Original language | English |
|---|---|
| Place of Publication | Espoo |
| Publisher | VTT Technical Research Centre of Finland |
| Number of pages | 40 |
| Publication status | Published - 2001 |
| MoE publication type | D4 Published development or research report or study |
Publication series
| Series | VTT Research Report |
|---|---|
| Number | TTE4-2001-24 |