Abstract | ||
---|---|---|
The speech breathing rate has been used for the early prediction of disease and detection of emotions. Most of the breath detection equipment are contact based. Here, we try to detect the speech breathing rate from speech recordings. Cepstrogram matrix is used as the feature for classifying the speech frames as breath or non-breath. The classifier used is the support vector machine (SVM) with a radial basis function (RBF) kernel. The classifier output is post-processed to join breathing segments which are closely spaced and remove breaths of small duration. The speech breathing rate is calculated from the breath to breath interval. The algorithm has been tested on a student evaluation database. When tested, the algorithm yields an F1 Score of 89% and root mean square error (RMSE) of 4.5 breaths/min for the speech-breathing rate. The breath segments have been validated by keenly listening to speech recordings and viewing thermal videos. |
Year | DOI | Venue |
---|---|---|
2019 | 10.23919/EUSIPCO.2019.8902730 | 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO) |
Keywords | Field | DocType |
Breath detection, cepstrogram, speech-breathing rate, SVM | Kernel (linear algebra),F1 score,Radial basis function,Computer science,Support vector machine,Mean squared error,Speech recognition,Respiratory rate,Breathing,Classifier (linguistics) | Conference |
ISSN | Citations | PageRank |
2076-1465 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohamed Ismail Yasar Arafath K | 1 | 0 | 0.34 |
Aurobinda Routray | 2 | 337 | 52.80 |