An Improved Method for Automatic Classification of Speech

Obstructive Sleep Apnea Syndrome (OSAS) is defined as a sleep related breathing disorder that causes the body to stop breathing for about 10 seconds and mostly ends with a loud sound due to the opening of the airway. OSAS is traditionally diagnosed using polysomnography, which requires a whole night stay at the sleep laboratory of a hospital, with multiple electrodes attached to the patient's body. Snoring is a symptom which may indicate the presence of OSAS; thus investigation of snoring sounds, which can be recorded in the patient's own sleeping environment, has become popular in recent years to diagnose OSAS. In this study, we aim to develop a new method to detect post-apnea snoring episodes with the goal of diagnosing apnea or creating new criteria similar to apnea / hypopnea index. Emphasis is placed on detecting post apnea episodes, hence the apnea periods. In this method, first segmentation is done to eliminate the silence parts. Then, these episodes are represented by distinctive features; some of these features are available in literature but some of them are novel. Finally, episodes are classified using supervised methods. False alarm rates are reduced by adding additional constraints into the detection algorithm. These methods are applied to snoring sound signals of OSAS patients, recorded in Gulhane Military Medical Academy, to verify the success of our algorithms.

show abstract

“…Then the probability distribution function is calculated by normalizing the spectrum of the frame over all frequencies [38]:…”

Section: Spectral Entropymentioning

confidence: 99%

Detection of post apnea sounds and apnea periods from sleep sounds

Karci

Doğrusöz

Çiloğlu

2011

2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

show abstract

“…Other features have also been considered. Alexandru Caruntu et al [13] have used zero-crossing density, Teager energy and entropy measures. Dhananjaya and Yegnanarayana [17] have used glottal activity detection, which in turn requires epoch extraction.…”

Section: Introductionmentioning

confidence: 99%

An Interesting Property of LPCs for Sonorant Vs Fricative Discrimination

Ananthapadmanabha,

Ramakrishnan,

Balachandran

2014

Preprint

View full text Add to dashboard Cite

Linear prediction (LP) technique estimates an optimum all-pole filter of a given order for a frame of speech signal. The coefficients of the all-pole filter, 1/A(z) are referred to as LP coefficients (LPCs). The gain of the inverse of the all-pole filter, A(z) at z = 1, i.e, at frequency = 0, A(1) corresponds to the sum of LPCs, which has the property of being lower (higher) than a threshold for the sonorants (fricatives). When the inverse-tan of A(1), denoted as T(1), is used a feature and tested on the sonorant and fricative frames of the entire TIMIT database, an accuracy of 99.07% is obtained. Hence, we refer to T(1) as sonorant-fricative discrimination index (SFDI). This property has also been tested for its robustness for additive white noise and on the telephone quality speech of the NTIMIT database. These results are comparable to, or in some respects, better than the state-of-the-art methods proposed for a similar task. Such a property may be used for segmenting a speech signal or for non-uniform frame-rate analysis.

show abstract