Perceptually based linear predictive analysis of speech

Abstract

A novel speech analysis method which uses several established psychoacoustic concepts. the perceptually based linear predictive analysis (PLP), nedels the auditory spectrum by the spectrum of the low-order all-pole model. The auditory spectrum is derived from the speech waveform by critical-band filtering. equal-loudness curve pre-emphasis. and intensityloudness root compression. we demonstrate through analysis of both synthetic and natural speech that psychoacoustic concepts of spectral auditory integration in vowel perception, namely the Fl, F2' concept of Carlson and Fant and the 3.5 Bark auditory integration concept of Chistovich, are well modeled by the PLP method. A complete speech analysis-synthesis system based on the PLP method is also described in the paper. INODUCTIONHuman speech contains a large amount of information. For speech recognition or low bit-rate speech compression applications, the relevant information is the phonetic information. All the other information in speech, such as information about the speaker's sex, identity. etc., is extraneous. The question of which parameters bear the phonetic information is a fundamental issue in speech research and has been extensively studied. Several studies indicate that a relatively small number of parameters is sufficient for complete phonetic specification of speech sounds.Low dimensionality of parametric speech representation is highly desirable for present machine speech processing techniques. The problem of lct-dirnensional parametric representation has been most studied for vowels. We discuss below the work which directly applies to our current research. Based on perceptual experiments, Carlson et al. [21 propose a two peak representation of vowels. The first spectral peak frequency Fl is identical with the first formant frequency of the vowel. The frequency of the second peak, denoted as P2', is determined by experimental phonetic match of the two-peak synthetic speech stimuli to the given vowel. We will refer to the concept of Carlson et al. as the Fl, P2' concept. Carlson et al. [31 and later Bladen [11 propose empirical formulae for P2' computation from the values of the four lowest ferment frequencies. The work [31 also deals with estimation of F2' values directly from the speech signal using histograms of the zerocrossing frequencies from closely spaced broad-band filters. Itahashi and Yokoyama [9] propose to extract the Fl and P2' peaks by 6th order all-pole modeling of the mel-warped high order (20th) LP system spectrum.Chistovich et al. [41 propose a concept in which the vowel spectrum is represented by major peeks. obtained by a two-stage process: peak extraction and auditory integration. She and her colleagues report that stimuli with peaks closer than 3 Bark can be approximated by one-peak stimuli with the peak position determined by the center of gravity of the two original peaks. When the distance between spectral peaks increases to more than 3.5 Bark, the one-peak representation is not possible. We will refer to the concept of Cbist...

Multiple Classifier Systems for the Classification of Audio-Visual Emotional States

“…The LPC coefficients are calculated over the critical band energies of a single frame, which is followed by the transformation of the LPC coefficients to cepstral values. In [7], PLP speech analysis was first introduced as a method to represent speech signals with respect to the human perception and with as few parameters as possible. However, PLP was, as most of the other analysis techniques, sensitive towards steady-state spectral factors caused by transmission channels, such as telephone recordings or the usage of different microphones [8].…”

A Review of Recent Advances in Speaker Diarization with Bayesian Methods

“…The majority of SD systems use Mel-Frequency Cepstral Coefficients (MFCC) as front-end features, although other feature spaces have been proposed, such as Linear Frequency Cepstral Coefficients (LFCC) and Perceptual Linear Predictive (PLP), (Hermansky et al, 1985). Some systems utilize prosodic features to augment the cepstral representation (see Friedland et al (2009)) while other approaches attempt to fuse several spaces and increase the diarization accuracy, (Gupta et al, 2007).…”

Morphologically Filtered Power-Normalized Cochleograms as Robust, Biologically Inspired Features for ASR

“…It is well established that feature extraction methods for ASR need to take into account properties of the HAS to a certain extent: the well-known Mel-Frequency Cepstral Coefficients (MFCC) [1], for example, result from non-linear transformations of the frequency domain that mimic Fletcher's psychophysical transfer function [2], and include a triangular Also widespread, Perceptually-based Linear Prediction (PLP) [3] is a pragmatic approach to model the auditory periphery that includes: resampling for frequency warping, barkscale filter-bank, limited frequency resolution, pre-emphasis according to the threshold of hearing, amplitude compression and smoothing using linear prediction. The computational complexity of PLP feature extraction is similar to MFCC and sometimes provides better recognition accuracy.…”