Linear predictive coding

About: Linear predictive coding is a research topic. Over the lifetime, 6565 publications have been published within this topic receiving 142991 citations. The topic is also known as: Linear predictive coding, LPC.

Pathological speech signal analysis and classification using empirical mode decomposition

Abstract: Automated classification of normal and pathological speech signals can provide an objective and accurate mechanism for pathological speech diagnosis, and is an active area of research. A large part of this research is based on analysis of acoustic measures extracted from sustained vowels. However, sustained vowels do not reflect real-world attributes of voice as effectively as continuous speech, which can take into account important attributes of speech such as rapid voice onset and termination, changes in voice frequency and amplitude, and sudden discontinuities in speech. This paper presents a methodology based on empirical mode decomposition (EMD) for classification of continuous normal and pathological speech signals obtained from a well-known database. EMD is used to decompose randomly chosen portions of speech signals into intrinsic mode functions, which are then analyzed to extract meaningful temporal and spectral features, including true instantaneous features which can capture discriminative information in signals hidden at local time-scales. A total of six features are extracted, and a linear classifier is used with the feature vector to classify continuous speech portions obtained from a database consisting of 51 normal and 161 pathological speakers. A classification accuracy of 95.7 % is obtained, thus demonstrating the effectiveness of the methodology.

Statistical Analysis of the Relationship between Audio and Video Speech Parameters for Australian English

Abstract: After decades of research, automatic speech processing has become more and more viable in recent years. Audio-video speech recognition has been shown to improve the recognition rate in noise-degraded environments. However, which audio and video speech parameters to choose for an optimal system and how they are related is still an open research issue. Here we present a number of statistical analyses that aim at increasing our understanding of such audio-video relationships. In particular, we look at the canonical correlation analysis and the coinertia analysis which investigate the relationship of linear combinations of parameters. The analyses are performed on Australian English as an example.

Speech quality measurement based on radio link parameters and objective measurement of received speech signals

Abstract: An improved method and system of measuring the perceived speech quality in mobile telecommunications networks is disclosed herein. In an embodiment of the invention, the method uses both radio link parameters and an objective measuring technique performed on received signals to estimate the speech quality perceived by the end-user. A radio link processing stage extracts temporal information from a set of available radio link parameters such as the BER, FER, RxLev, handover statistics, soft information, and speech energy. Concurrently, a speech processing stage is used to process a sequence of original signals and received signals, obtained from the output of a telecommunications system. The signal sequences are processed by an objective measuring technique such as Perceptual Speech Quality Measure (PSQM). The outputs from the radio link processing and speech processing stages are utilized to calculate an estimate for speech quality. Furthermore, a weight may be given to radio link processing and speech processing in accordance with their performance under various conditions such that the overall speech quality is calculated with respect to the best approach.

Enhancing sparsity in linear prediction of speech by iteratively reweighted 1-norm minimization

Abstract: Linear prediction of speech based on 1-norm minimization has already proved to be an interesting alternative to 2-norm minimization. In particular, choosing the 1-norm as a convex relaxation of the 0-norm, the corresponding linear prediction model offers a sparser residual better suited for coding applications. In this paper, we propose a new speech modeling technique based on reweighted 1-norm minimization. The purpose of the reweighted scheme is to overcome the mismatch between 0-norm minimization and 1-norm minimization while keeping the problem solvable with convex estimation tools. Experimental results prove the effectiveness of the reweighted 1-norm minimization, offering better coding properties compared to 1-norm minimization.

Variants of cepstrum based speaker identity verification

Abstract: Analysis parameters and various distance measures are investigated for a template matching scheme for speaker identity verification (SIV). Two parameters are systematically varied-the length of the signal analysis window, and the order of the linear predictive coding/-cepstrum analysis. Computational costs associated with the choice of parameters are also considered. The distance measures tested are the Euclidean, inverse variance weighting, differential mean weighting, Kahn's simplified weighting, the Mahalanobis distance, and the Fisher linear discriminant. Using the equal error rate (EER) of pairwise utterance dissimilarity distributions, performance is estimated for prespecified and (a simulation of) user-determined input vocabulary. Performance varies significantly across vocabulary, and average performance is approximately 5% EER for the better algorithms on telephone speech. >