We need to be able to search for keywords that are spoken, images can now be searched but can the spoken word? When somebody says something on the radio you have to record the programme and then skip back with a fiddly slider and have to guess at what time code you heard it at. How impractical is this. This is the same as good old VHS! In summary:
- needs fixing
Solution: ACR audio character recognitions similar to OCR that enables text in images be turned into text that is searchable.