Exploration of vowel onset and offset points for hybrid speech segmentation

Abstract

Automatic segmentation of speech using embedded reestimation of monophone hidden Markov models (HMMs) followed by forced alignment may not give accurate boundaries. Group delay (GD) processing for refining the boundaries at the syllable level is attempted earlier. This paper aims at exploring vowel onset point (VOP) and vowel offset or end point (VEP) for correcting the boundaries obtained using HMM alignment. HMM models the class information well, however may not detect the exact boundary. In case of VOPs and VEPs, spurious rate or miss rate can be there, but detected boundaries are more accurate. Combining both HMM and VOP/VEP gives improvement in terms of log likelihood scores of forced aligned phoneme boundaries. HMM boundaries are corrected using VOP/VEP and model parameters are reestimated at the syllable level. Results are compared with that of GD based correction and found that overall performance is comparable. Performance for vowels is found to be higher than that of GD based refinement as the refinement in this case is mainly at the vowel boundaries. HMM based speech synthesis systems (HTS) are developed using phone as a basic unit with the proposed segmentation method. Subjective evaluation indicates that there is an improvement in the quality of synthesis.

SLoClas: A Database for Joint Sound Localization and Classification

“…Using this manually marked starting label, we synchronize the source (loudspeaker) signal and the 4-channel recorded audio signals. Considering the start of the audio as an anchor point, we segment all the sample sounds with energy based evidence [27,28,29] and manual observation. In this way, we achieve 988 segmented audio files and a TSP signal for each DOA angle.…”

Speech Segmentation Using Dynamic Windows and Thresholds for Arabic and English Languages

“…Other approaches are based on Hidden Markov Model (HMM) (Daniel and James, 2017) such as (Lefevre et al, 2002) that combines a K-Means classifier with Hidden Markov Models in order to analyze audio segment using several audio features based either on segment or frame. Another method base on HMM is (Biswajit et al, 2015) that aims at exploring Vowel Onset Point (VOP) and Vowel offset or End Point (VEP) for correcting the boundaries obtained using HMM alignment. HMM models the class information well, but it may not detect the exact boundary.…”

Sonority Measurement Using System, Source, and Suprasegmental Information

“…In literature, sonorant segmentation is performed by using mel frequency cepstral coefficients (MFCCs), knowledge based acoustic features or a combination of both [2], [24]. Recently in [23], [25], features based on both spectral and source information are proposed and a hierarchical algorithm is developed to detect sonorant and non-sonorant regions in continuous speech. However, the feature may not have potential to further divide the sonorant regions based on the degree of sonority associated with the sound.…”