Research on snores for Obstructive Sleep Apnea Syndrome (OSAS) diagnosis is a new trend in recent years. In this paper, we proposed a snore-based apnea and hypopnea events classification approach. Firstly,we define the snores after the apnea event and during the hypopnea event as apnea-eventsnore (AES) and hypopnea-event-snore (HES), respectively. Then, we design a new feature from the trend of the amplitude spectrum of snores. The newly proposed feature can be viewed as an improvement of the Mel-frequency cepstral coefficient (MFCC) feature, which is well-known for speech recognition. The extracted features were fed to principle component analysis (PCA) for dimension reduction and support vector machine (SVM) for apnea and hypopnea events classification. The experimental results demonstrate the efficiency of the proposed algorithm in using snores to classify apnea and hypopneaevents.