Back to results
US 6,285,979 B1Granted
Phoneme analyzer
AssigneeAVR Communications Ltd.
InventorsBoris Ginzburg, Barak Dar
Life of this patent
Estimating the term…
Abstract
Phoneme analysis is carried out in real time by detecting a voiced component in the range of 200 Hz to 1 KHz and simultaneously detecting voiceless components having frequencies greater than about 2.4 KHz and greater than about 3.4 KHz, respectively, to produce respective outputs which are logically combined to produce two-bit logic signals which can be used to control a speech processing device.
Claims12
A real-time method of analyzing speech for phonemes contained therein comprising the steps of:
- (a) obtaining a speech signal containing voiced vowel sounds, low frequency voiceless sounds and high frequency voiceless sounds;
- (b) detecting in said speech signal a voiced component having a frequency in a range of 200 Hz to about 1 KHz and generating a first output when said frequency in said range of 200 Hz to about 1 KHz is present in said speech signal;
- (c) simultaneously detecting in said speech signal a voiceless component having a frequency greater than about 2.4 KHz and generating a second output when said frequency greater than about 2.4 KHz is present in said speech signal;
- (d) simultaneously detecting in said speech signal a voiceless component having a frequency greater than about 3.4 KHz and generating a third output when said frequency greater than about 3.4 KHz is present in said speech signal;
- (e) logically combining said first, second and third outputs to produce two-bit logic signals representing high-frequency voiceless sound phonemes, lower-frequency voiceless sound phonemes, selected vowel sound and other voiced sound phonemes;
- and
- (f) controlling a speech processing device with said two-bit logic signals.
4 more elements
An apparatus for real-time phoneme analysis of speech, said apparatus comprises:
- input means for obtaining a speech signal containing voiced vowel sounds, low frequency voiceless sounds and high frequency voiceless sounds;
- means connected to said input means for detecting said in said speech signal a voiced component having a frequency in a range of about 200 Hz to about 1 KHz and generating a first output when said frequency in said range of 200 Hz to about 1 KHz is present in said speech signal;
- means connected to said input means for simultaneously detecting in said speech signal a voiceless component having a frequency greater than about 3.4 KHz and generating a third output when said frequency greater than about 3.4 KHz is present in said speech signal;
- means for logically combining said first, second and third outputs to produce two-bit logic signals representing high-frequency voiceless sound phonemes, lower frequency voiceless sound phonemes, selected vowel sound and other voiced sound phonemes;
- and
- means for controlling a speech processing device with said two-bit logic signals.
3 more elements
Dependencies are inferred from the claim text.