Last modified 10 years ago Last modified on 03/31/09 15:13:58

Silence Detection Scripts

Other Resources


Resources to aid in the segmentation of speech:



An approach:

train the system on a small amount of manually
transcribed speech (.wav and .lab) and then use it to transcribe a
larger amount of untranscribe speech (only with .wav).  If the
confidence level is high enough, then add into the
trainning data and the process will be run iteratively until all the
untranscribe speech is added to the trainning data.

Manual Speech Transcription Tools

Another manual approach for getting audio transcriptions:

A technique I have used with great success is to set things up so that I 
repeat the foreign voice with my own voice to my second computer which has 
windows voice recognition.

Assume you have a track of a foreign (=unrecognizable by your dictation 
software) voice loaded into Audacity in one computer, and you have a second
 computer with voice recognition software trained to your own voice.

Now you wear a headset with noise cancelling microphone connected to the 
second computer and start playing back the track on the first computer via 
loudspeaker. As you hear the voice you speak the same words into the mike
 and the VR software transcribes it for you. Audacity is good for this with 
keyboard shortcuts for play and pause etc. Noise cancelling mike is 
important otherwise you pick up the loudspeakers. It takes a bit of 
practice but can be done.