11-08-2012, 02:59 PM
Basics of Speech Recognition Systems
[attachment=31144]
Introduction
Current software systems -
Dragon
Windows 7
VoiceXML
Sound recognition – a natural act than any other
Will lead our life in more intuitive way
More user friendly & interactive.
How our brain goes about it ?
Why can’t a dumb speak ?
Why can’t child speak ?
Have you ever stumbled upon a word – that you thought is different which others mean a different one ?
Brain is first to be trained & then used.
The frequency Spectrum of word “Hello”
Every time a user speaks a word it sounds different. Users do not produce exactly the same sound for the same phoneme.
The background noise from the microphone and user’s office sometimes causes the recognizer to hear a different vector than it would have if the user was in a quiet room with a high quality microphone.
The sound of a phoneme changes depending on what phonemes surround it. The "t" in "talk" sounds different than the "t" in "attack" and "mist".
The sound produced by a phoneme changes from the beginning to the end of the phoneme, and is not constant. The beginning of a "t" will produce different feature numbers than the end of a "t".
[attachment=31144]
Introduction
Current software systems -
Dragon
Windows 7
VoiceXML
Sound recognition – a natural act than any other
Will lead our life in more intuitive way
More user friendly & interactive.
How our brain goes about it ?
Why can’t a dumb speak ?
Why can’t child speak ?
Have you ever stumbled upon a word – that you thought is different which others mean a different one ?
Brain is first to be trained & then used.
The frequency Spectrum of word “Hello”
Every time a user speaks a word it sounds different. Users do not produce exactly the same sound for the same phoneme.
The background noise from the microphone and user’s office sometimes causes the recognizer to hear a different vector than it would have if the user was in a quiet room with a high quality microphone.
The sound of a phoneme changes depending on what phonemes surround it. The "t" in "talk" sounds different than the "t" in "attack" and "mist".
The sound produced by a phoneme changes from the beginning to the end of the phoneme, and is not constant. The beginning of a "t" will produce different feature numbers than the end of a "t".