Estimation of glottal closure instants from degraded speech using a phase-difference-based algorithm. (November 2017)

• Record Type: Journal Article
• Authors: Anushiya Rachel, G.; Vijayalakshmi, P.; Nagarajan, T.
• Is Part Of: Computer speech & language. Volume 46(2017)
• Page Start: 136
• Page End: 153
• Publication Date: 2017-11
• Subjects: Glottal closure instants -- Phase difference -- Group delay -- Degraded speech -- Telephone -- Noisy -- Pathological; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2017.05.008
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A phase-difference-based algorithm is used to estimate GCIs from degraded speech. The phase-difference at the angular location of a zero lying outside the unit circle is shown to be 2π The algorithm is more robust to degradations in speech, when evaluated on telephone, noisy, and pathological speech, compared to existing algorithms. On telephone and pathological speech, the IDR is at least 7–10.% greater than that of existing algorithms. A new metric, namely, the Spurious Instants Rate in Non-voiced regions (SIRN) has been proposed to evaluate the performance of algorithms in non-voiced regions. The phase-difference algorithm is observed to scarcely estimate GCIs in non-voiced regions and results in a significantly lower SIRN, compared to existing algorithms. Abstract: The estimation of glottal closure instants (GCIs) plays a vital role in several glottal synchronous applications, and may not be restricted to clean speech. This necessitates the development of a GCI estimation algorithm that performs as well on degraded speech as on clean speech. Degradations in speech may be in the form of spectral or temporal perturbations. This could result in several spurious discontinuities, as in noisy speech, excitations that are not well-defined, as in band-limited speech, aperiodicity and variations in amplitude, as in pathological speech, thereby making the task of identifying GCIs more challenging. In this regard, a conditional group-delay/phase-difference-based (PD) algorithm that was initially proposed for use on clean speech is extended to operate on degraded speech, specifically telephone, noisy, and pathological speech. The performance of this algorithm is compared with six existing algorithms, in terms of identification, false alarm, and miss rates, and identification accuracy. It is observed that the PD algorithm is robust to degradations in speech and performs better than or on par with existing algorithms in all cases considered. Further, it is also observed that unlike existing algorithms, the PD algorithm scarcely estimates GCIs in non-voiced regions and this is verified in terms of a new metric proposed in the paper, namely, the spurious instants rate in non-voiced regions.