Formant estimation of speech and singing voice by combining wavelet with LPC and Cepstrum techniques

Loni, Deepali Yoginath; Subbaraman, Shaila

doi:10.1109/iciinfs.2014.7036530

Cited by 12 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vibrato extraction begins with the analysis of pitch of singing voice, to identify its periodic variations around an average value. To compute pitch of the singing voice, we used the Cepstrum technique, as this method efficiently separates the excitation signal (enclosing vibration of the vocal folds) from the vocal tract [37]. We set the grid limit of vibrato extent to the maximum range of ± 1.5 semitone to extract the vibrato portion from the pitch contour.…”

Section: Vibrato Of Singing Voicementioning

confidence: 99%

Robust singer identification of Indian playback singers

Loni

Subbaraman²

2019

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

Singing voice analysis has been a topic of research to assist several applications in the domain of music information retrieval system. One such major area is singer identification (SID). There has been enormous increase in production of movies and songs in Bollywood industry over the last 50 decades. Surveying this extensive dataset of singers, the paper presents singer identification system for Indian playback singers. Four acoustic features namely-formants, harmonic spectral envelope, vibrato, and timbre-that uniquely describe the singer are extracted from the singing voice segments. Using the combination of these multiple acoustic features, we address the major challenges in SID like the variations in singer's voice, testing of multilingual songs, and the album effect. Systematic evaluation shows the SID is robust against the variations in singer's singing style and structure of songs and is effective in identifying the cover songs and singers. The results are investigated on in-house cappella database consisting of 26 singers and 550 songs. By performing dimension reduction of the feature vector and using Support Vector Machine classifier, we achieved an accuracy of 86% using fourfold cross validation process. In addition, performance comparison of the proposed work with other existing approaches reveals the superiority in terms of volume of dataset and song duration.

show abstract

Section: Vibrato Of Singing Voicementioning

confidence: 99%

Robust singer identification of Indian playback singers

Loni

Subbaraman²

2019

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The problems involved in recognising words being sung under noisy background conditions, has been a topic of interest to many researchers [1–8] especially the task of recognising words mixed with several musical instruments. Another issue in singing voice recognition is that the problem is quite different from speech recognition (SR) or ASR because of substantial differences between speaking and singing voices such as the duration of vocal sounds, the volume, pitch, vibrato, formant, rhythm and rhyme [9–16]. To make the problem realistic and feasible, we considered singing voices in a polyphonic audio signal sampled from commercial compact‐discs (CD) or DVDs of popular music recordings.…”

Section: Introductionmentioning

confidence: 99%