Tuesday, November 19, 2013

New Czech recognizer online

We are happy to announce that our new Czech recognizer is online at spokendata.com. The novelty lies in the support of 16kHz audio data (so called wideband) and also in robustness for distant microphones.
In comparison to the previous Czech recognizer, which was aimed at telephone data (8kHz - so called narrowband), the new one achieves better accuracy for:
  • Speech recorded with higher quality - 16kHz or more. Unless you capture a telephone call, you usually record the data up to 44kHz.
  • Distant microphone recordings. A telephone call recording is usually labeled as a close-talk because the speaker's mouth is close to the microphone. The distant microphone is the opposite case. Here the speaker's mouth is far from the microphone. As an example it can be a voice recorder or a mobile phone lying on the table while recording a dialog.
Fell free to test the recognizer by uploading your data and enjoy the transcript.