Modeling of the glottal flow derivative waveform with application to speaker identification

Abstract

Speech production has long been viewed as a linear filtering process, as described by Fant in the late 1950's [10]. The vocal tract, which acts as the filter, is the primary focus of most speech work. This thesis develops a method for estimating the source of speech, the glottal flow derivative. Models are proposed for the coarse and fine structure of the glottal flow derivative, accounting for nonlinear sourcefilter interaction, and techniques are developed for estimating the parameters of these models. The importance of the source is demonstrated through speaker identification experiments.The glottal flow derivative waveform is estimated from the speech signal by inverse filtering the speech with a vocal tract estimate obtained during the glottal closed phase. The closed phase is determined through a sliding covariance analysis with a very short time window and a one sample shift. This allows calculation of formant motion within each pitch period predicted by Ananthapadmanabha and Fant to be a result of nonlinear source-filter interaction during the glottal open phase [1]. By identifying the timing of formant modulation from the formant tracks, the timing of the closed phase can be determined. The glottal flow derivative is modeled using an LF model to capture the coarse structure, while the fine structure is modeled through energy measures and a parabolic fit to the frequency modulation of the first formant.The model parameters are used in the Reynolds Gaussian Mixture Model Speaker Identification system with excellent results for non-degraded speech. Each category of source features is shown to contain speaker dependent information, while the combination of source and filter parameters increases the overall accuracy for the system. For a large dataset, the coarse structure parameters achieve 60% accuracy, the fine structure parameters give 40% accuracy, and their combination yields 70% correct identification. When combined with vocal tract features, the accuracy increases to 93%, slightly above the accuracy achieved with just vocal tract information. On smaller datasets of telephone-degraded speech, accuracy increases up to 20% when source features are added to traditional mel-cepstral measures. Perhaps one of his best contributions is that he and I tend to think of things from different angles, hopefully I will carry his viewpoint along with my own after I leave MIT. I would also like to thank Doug Reynolds for helping me understand and use his speaker identification system. Thanks are also owed to all the members of the Speech System Technology Group who have helped me in so many ways. I would also like to thank all the people who thought it would be a shame for me to not get an advanced degree and all my friends in Seattle who signed their letters "quit school."These conflicting views enabled me to make up my own mind with a minimum of outside pressure.And, of course, I wish to thank the sponsors of my research and my time here at MIT. I would like to thank the EECS department for awarding me a fe...

Robustness of group delay representations for noisy speech signals

“…For speech signals, the zeros are introduced by pitch, nasals and the short-time analysis window function. Further, zeros are also introduced by the glottal return phase (the time interval between the most negative value of the glottal flow derivative and glottal closure [Plumpe et al (1999)] when the glottal flow is modelled as a linear filter [Doval et al (2003)]. The presence of zeros makes the denominator term in Equation 3 vanish, leading to an illbehaved group delay function.…”

Glottal mixture model (GLOMM) for speaker identification on telephone channels

“…The linear predictive coding (LPC) coefficients are readily estimated using classical methods. In addition to providing a good approximation to the vocal tract filter (VTF), the prediction error waveform is a first-order approximation to the voice source waveform (VSW), which approximates the derivative of the glottal flow [2]. Refer to Figure 1, which is a block-diagram of GLOMM.…”

“…It is logical, then, that much speaker-related information is missing from MFCC. Attempts to add voice source information back into speaker identification systems to improve them have met limited success [1], [2], [3], [4], probably due to the difficulty and reliability of estimating the voice source waveform itself. We previously introduced the GLOMM method [5], which was based on detecting glottal events (glottal opening/closing) by detecting times of high linear prediction error.…”

Glottal Source Estimation Using an Automatic Chirp Decomposition

“…While techniques for modeling the vocal tract are rather well-established, it is not the case for the glottal source representation. However the characterization of this latter has been shown to be advantageous in speaker recognition [1], speech disorder analysis [2], speech recognition [3] or speech synthesis [4]. These reasons justify the need of developing algorithms able to robustly and reliably estimate and parametrize the glottal signal.…”