(0)G10L:0/0:
IPC6
SECTION G - PHYSICS
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION
G10L
1/1

G 10 L

SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION (measurement of sound waves in general G 01 H; frequency spectrum analysis of electric signals in general G 01 R 23/16; electrophonic musical instruments G 10 H; sound-producing devices other than musical instruments G 10 K; information storage, e.g. sound storage, G 11; coding, decoding or code conversion, in general H 03 M) [4]

 

 

 

 

3
/ 00 Details of devices which are not related to a specific method of analysis or synthesis [4]

3
/ 02 Devices for modifying at least one characteristic of the speech waves, e.g. amplitude, basic frequency, frequency spectrum, duration (audiometry A 61 B 5/12; modifications of communication systems to reduce bandwidth of signals H 04 B 1/66) [4]  
 

5
/ 00 Methods or devices for speech analysis, synthesis or recognition using more than one specific type of device or method covered by group G 10 L 7/00 or G 10 L 9/00 [4]

5
/ 02 Speech synthesis from stored data [4]  

5
/ 04 the stored data being speech elements, e.g. phonemes [4]  

5
/ 06 for recognition or speaker identification [4]  
 

7
/ 00 Methods or devices using the amplitude-frequency representation of speech waves [4]

7
/ 02 for analysis or synthesis [4]  

7
/ 04 using filter banks [4]  

7
/ 06 using Fourier or Walsh transformation (computers for forming Fourier or Walsh transformations G 06 F 17/14, G 06 G 7/19) [4]  

7
/ 08 for speech recognition, for speaker identification, for controlling machines by voice, e.g. controlling typewriters [4]  

7
/ 10 for displaying speech waves; Spectrographs (G 10 L 7/08 takes precedence) [4]  
 

9
/ 00 Methods or devices using other specified techniques (computers in general G 06) [4]

9
/ 02 using formants identification or reconstruction (G 10 L 9/04 takes precedence) [4]  

9
/ 04 using formants extraction from characteristics of the spectral envelope [4]  

9
/ 06 for recognition, for speaker identification or for controlling machines by voice [4]  

9
/ 08 using correlation techniques [4]  

9
/ 10 using simulation of the vocal and aural systems [4]  

9
/ 12 using zero crossing techniques (G 10 L 9/02 takes precedence) [4]  

9
/ 14 using predictive techniques [4]  

9
/ 16 using orthogonal functions [4]  

9
/ 18 using digital techniques (G 10 L 9/02 to G 10 L 9/16 take precedence) [4]  

9
/ 20 using non-electrical techniques [4]