A perceptually-motivated low-complexity instantaneous linear channel normalization technique applied to speaker verification. (May 2015)

• Record Type: Journal Article
• Authors: Poblete, Victor; Espic, Felipe; King, Simon; Stern, Richard M.; Huenupán, Fernando; Fredes, Josué; Yoma, Nestor Becerra
• Is Part Of: Computer speech & language. Volume 31(2015)
• Page Start: 1
• Page End: 27
• Publication Date: 2015-05
• Subjects: Channel robust feature extraction -- Auditorymodels -- Spectral local normalization -- Synchrony detection; 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.2014.10.006
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract : Highlights: A novel method to instantaneously normalize speech features is proposed (LNCC). LNCC does not need any alterations to the statistical modeling. LNCC dramatically compensates for static spectral tilts. LNCC can be more robust to time varying spectral tilts than standard methods. LNCC does not require the computation and storage of additional statistics. Abstract: This paper proposes a new set of speech features called Locally-Normalized Cepstral Coefficients (LNCC) that are based on Seneff's Generalized Synchrony Detector (GSD). First, an analysis of the GSD frequency response is provided to show that it generates spurious peaks at harmonics of the detected frequency. Then, the GSD frequency response is modeled as a quotient of two filters centered at the detected frequency. The numerator is a triangular band pass filter centered around a particular frequency similar to the ordinary Mel filters. The denominator term is a filter that responds maximally to frequency components on either side of the numerator filter. As a result, a local normalization is performed without the spurious peaks of the original GSD. Speaker verification results demonstrate that the proposed LNCC features are of low computational complexity and far more effectively compensate for spectral tilt than ordinary MFCC coefficients. LNCC features do not require the computation and storage of a moving average of the feature values, and they provide relative reductions in Equal Error Rate (EER) as high as 47.7%, 34.0% or 25.8% when compared with MFCC, MFCC + CMN, or MFCC + RASTA in one case of variable spectral tilt, respectively.