Colin
01-13-2012, 08:01 AM
Hi
I have a Client who is looking for a piece of software which will process audio files. What the software needs to do is recognise when numbers are spoken and somehow blank them out from the audio file.
So for example the audio file might currently say...
"My phone number is zero one two three four five six seven eight nine, can you let me know by six o'clock"
And we would want that to say, after processing...
"My phone number is *bleep* *bleep* *bleep* *bleep* *bleep* *bleep* *bleep**bleep* *bleep*, can you let me know by *bleep* o'clock"
I understand AudioLab is able to process audio, and IntelligenceLab can be trained to recognize patterns, including audio patterns captured with AudioLab. It would therefore appear possible to build this solution using these tools.
Would anyone be able to undertake this project and complete it within the next couple of weeks, say by end Jan 2012?
Thanks in Advance
Colin
I have a Client who is looking for a piece of software which will process audio files. What the software needs to do is recognise when numbers are spoken and somehow blank them out from the audio file.
So for example the audio file might currently say...
"My phone number is zero one two three four five six seven eight nine, can you let me know by six o'clock"
And we would want that to say, after processing...
"My phone number is *bleep* *bleep* *bleep* *bleep* *bleep* *bleep* *bleep**bleep* *bleep*, can you let me know by *bleep* o'clock"
I understand AudioLab is able to process audio, and IntelligenceLab can be trained to recognize patterns, including audio patterns captured with AudioLab. It would therefore appear possible to build this solution using these tools.
Would anyone be able to undertake this project and complete it within the next couple of weeks, say by end Jan 2012?
Thanks in Advance
Colin