Title :
The demographics of speaker independent digit recognition
Author_Institution :
Texas Instrum. Inc., Dallas, TX, USA
Abstract :
A database designed to provide a statistically significant model of the demographics of the continental US population is presented. Recognition performance on a simple digit recognition task is analyzed and shown to be most highly correlated with signal-to-noise ratio, dialect, and age. Several other demographic features, including sex, income level, education level, and market size, are found to have little correlation with recognition error rate
Keywords :
database management systems; linguistics; speech analysis and processing; speech recognition; telecommunications computing; Voice Across America database; age; continental US population; database; demographic features; demographics; dialect; digit recognition task; recognition error rate; signal-to-noise ratio; speaker independent digit recognition; statistically significant model; Demography; Error analysis; Image databases; Instruments; Laboratories; Performance analysis; Robustness; Signal analysis; Signal to noise ratio; Spatial databases; Speech recognition; Telephony;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Conference_Location :
Albuquerque, NM
DOI :
10.1109/ICASSP.1990.115549
