Library - View details   To know more about this section

Speech and monophonic singing segmentation using pitch parameters

Article: English. Online
Author(s)
Navas Cordón, Eva ; Sarasola, Xabier ; Saratxaga, Ibon ; Serrano, Luis ; Tavarez, David
Title
Speech and monophonic singing segmentation using pitch parameters / Xabier Sarasola, Eva Navas, David Tavarez, Luis Serrano, Ibon Saratxaga
In
Iberspeech 2018, Barcelona, november 21-23 : program and proceedings, , 147-151
Subjects
Bertsolaritza
Content
Testu osoa
Other authors
EHU. Aholab taldea
Type of material
Article
Eduki mota
Jardunaldiak, biltzarrak
Notes
Bibliografia: 151 or.
In this paper we present a novel method for automatic segmentation of speech and monophonic singing voice based only on two parameters derived from pitch: proportion of voiced segments and percentage of pitch labelled as a musical note. First, voice is located in audio files using a GMM-HMM based VAD and pitch is calculated. Using the pitch curve, automatic musical note labelling is made applying stable value sequence search. Then pitch features extracted from each voice island are classified with Support Vector Machines. Our corpus consists in recordings of live sung poetry sessions where audio files contain both singing and speech voices. The proposed system has been compared with other speech/singing discrimination systems with good results.