Feature Extraction Methods Based on Linear Predictive Coding and Wavelet Packet Decomposition for Recognizing Spoken Words in Malayalam

Speech signals are one of the most important means of communication among the human beings. In this paper, a comparative study of two feature extraction techniques are carried out for recognizing speaker independent spoken isolated words. First one is a hybrid approach with Linear Predictive Coding (LPC) and Artificial Neural Networks (ANN) and the second method uses a combination of Wavelet Packet Decomposition (WPD) and Artificial Neural Networks. Voice signals are sampled directly from the microphone and then they are processed using these two techniques for extracting the features. Words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. Training, testing and pattern recognition are performed using Artificial Neural Networks. Back propagation method is used to train the ANN. The proposed method is implemented for 50 speakers uttering 20 isolated words each. Both the methods produce good recognition accuracy. But Wavelet Packet Decomposition is found to be more suitable for recognizing speech because of its multi-resolution characteristics and efficient time frequency localizations

PSWT Based Linear Predictive Coding and Development of a Parallel Multiple Subsequence Structure for DWT Computation

During 1990's the Wavelet Transform emerged as an important signal processing tool with potential applications in time-frequency analysis and non-stationary signal processing.Wavelets have gained popularity in broad range of disciplines like signal/image compression, medical diagnostics, boundary value problems, geophysical signal processing, statistical signal processing,pattern recognition,underwater acoustics etc.In 1993, G. Evangelista introduced the Pitch- synchronous Wavelet Transform, which is particularly suited for pseudo-periodic signal processing.The work presented in this thesis mainly concentrates on two interrelated topics in signal processing,viz. the Wavelet Transform based signal compression and the computation of Discrete Wavelet Transform. A new compression scheme is described in which the Pitch-Synchronous Wavelet Transform technique is combined with the popular linear Predictive Coding method for pseudo-periodic signal processing. Subsequently,A novel Parallel Multiple Subsequence structure is presented for the efficient computation of Wavelet Transform. Case studies also presented to highlight the potential applications.

A non-linear VAD for noisy environments

This paper deals with non-linear transformations for improving the performance of an entropy-based voice activity detector (VAD). The idea to use a non-linear transformation has already been applied in the field of speech linear prediction, or linear predictive coding (LPC), based on source separation techniques, where a score function is added to classical equations in order to take into account the true distribution of the signal. We explore the possibility of estimating the entropy of frames after calculating its score function, instead of using original frames. We observe that if the signal is clean, the estimated entropy is essentially the same; if the signal is noisy, however, the frames transformed using the score function may give entropy that is different in voiced frames as compared to nonvoiced ones. Experimental evidence is given to show that this fact enables voice activity detection under high noise, where the simple entropy method fails.

Source separation techniques applied to linear prediction

The prediction filters are well known models for signal estimation, in communications, control and many others areas. The classical method for deriving linear prediction coding (LPC) filters is often based on the minimization of a mean square error (MSE). Consequently, second order statistics are only required, but the estimation is only optimal if the residue is independent and identically distributed (iid) Gaussian. In this paper, we derive the ML estimate of the prediction filter. Relationships with robust estimation of auto-regressive (AR) processes, with blind deconvolution and with source separation based on mutual information minimization are then detailed. The algorithm, based on the minimization of a high-order statistics criterion, uses on-line estimation of the residue statistics. Experimental results emphasize on the interest of this approach.

Modified Block Adaptive Predictive Coder For Speech Processing

This thesis investigated the potential use of Linear Predictive Coding in speech communication applications. A Modified Block Adaptive Predictive Coder is developed, which reduces the computational burden and complexity without sacrificing the speech quality, as compared to the conventional adaptive predictive coding (APC) system. For this, changes in the evaluation methods have been evolved. This method is as different from the usual APC system in that the difference between the true and the predicted value is not transmitted. This allows the replacement of the high order predictor in the transmitter section of a predictive coding system, by a simple delay unit, which makes the transmitter quite simple. Also, the block length used in the processing of the speech signal is adjusted relative to the pitch period of the signal being processed rather than choosing a constant length as hitherto done by other researchers. The efficiency of the newly proposed coder has been supported with results of computer simulation using real speech data. Three methods for voiced/unvoiced/silent/transition classification have been presented. The first one is based on energy, zerocrossing rate and the periodicity of the waveform. The second method uses normalised correlation coefficient as the main parameter, while the third method utilizes a pitch-dependent correlation factor. The third algorithm which gives the minimum error probability has been chosen in a later chapter to design the modified coder The thesis also presents a comparazive study beh-cm the autocorrelation and the covariance methods used in the evaluaiicn of the predictor parameters. It has been proved that the azztocorrelation method is superior to the covariance method with respect to the filter stabf-it)‘ and also in an SNR sense, though the increase in gain is only small. The Modified Block Adaptive Coder applies a switching from pitch precitzion to spectrum prediction when the speech segment changes from a voiced or transition region to an unvoiced region. The experiments cont;-:ted in coding, transmission and simulation, used speech samples from .\£=_‘ajr2_1a:r1 and English phrases. Proposal for a speaker reecgnifion syste: and a phoneme identification system has also been outlized towards the end of the thesis.

Método para reconhecimento de vogais e extração de parâmetros acústicos para analises forenses

Forensic speaker comparison exams have complex characteristics, demanding a long time for manual analysis. A method for automatic recognition of vowels, providing feature extraction for acoustic analysis is proposed, aiming to contribute as a support tool in these exams. The proposal is based in formant measurements by LPC (Linear Predictive Coding), selectively by fundamental frequency detection, zero crossing rate, bandwidth and continuity, with the clustering being done by the k-means method. Experiments using samples from three different databases have shown promising results, in which the regions corresponding to five of the Brasilian Portuguese vowels were successfully located, providing visualization of a speaker’s vocal tract behavior, as well as the detection of segments corresponding to target vowels.

Developing a Child Friendly Text-to-Speech System

This paper discusses the implementation details of a child friendly, good quality, English text-to-speech (TTS) system that is phoneme-based, concatenative, easy to set up and use with little memory. Direct waveform concatenation and linear prediction coding (LPC) are used. Most existing TTS systems are unit-selection based, which use standard speech databases available in neutral adult voices.Here reduced memory is achieved by the concatenation of phonemes and by replacing phonetic wave files with their LPC coefficients. Linguistic analysis was used to reduce the algorithmic complexity instead of signal processing techniques. Sufficient degree of customization and generalization catering to the needs of the child user had been included through the provision for vocabulary and voice selection to suit the requisites of the child. Prosody had also been incorporated. This inexpensive TTS systemwas implemented inMATLAB, with the synthesis presented by means of a graphical user interface (GUI), thus making it child friendly. This can be used not only as an interesting language learning aid for the normal child but it also serves as a speech aid to the vocally disabled child. The quality of the synthesized speech was evaluated using the mean opinion score (MOS).

Predictive-DCT Coding for 3D Mesh Sequences Compression

This paper proposes a new compression algorithm for dynamic 3d meshes. In such a sequence of meshes, neighboring vertices have a strong tendency to behave similarly and the degree of dependencies between their locations in two successive frames is very large which can be efficiently exploited using a combination of Predictive and DCT coders (PDCT). Our strategy gathers mesh vertices of similar motions into clusters, establish a local coordinate frame (LCF) for each cluster and encodes frame by frame and each cluster separately. The vertices of each cluster have small variation over a time relative to the LCF. Therefore, the location of each new vertex is well predicted from its location in the previous frame relative to the LCF of its cluster. The difference between the original and the predicted local coordinates are then transformed into frequency domain using DCT. The resulting DCT coefficients are quantized and compressed with entropy coding. The original sequence of meshes can be reconstructed from only a few non-zero DCT coefficients without significant loss in visual quality. Experimental results show that our strategy outperforms or comes close to other coders.

Side information creation for efficient Wyner-Ziv video coding: Classifying and reviewing

Video coding technologies have played a major role in the explosion of large market digital video applications and services. In this context, the very popular MPEG-x and H-26x video coding standards adopted a predictive coding paradigm, where complex encoders exploit the data redundancy and irrelevancy to 'control' much simpler decoders. This codec paradigm fits well applications and services such as digital television and video storage where the decoder complexity is critical, but does not match well the requirements of emerging applications such as visual sensor networks where the encoder complexity is more critical. The Slepian Wolf and Wyner-Ziv theorems brought the possibility to develop the so-called Wyner-Ziv video codecs, following a different coding paradigm where it is the task of the decoder, and not anymore of the encoder, to (fully or partly) exploit the video redundancy. Theoretically, Wyner-Ziv video coding does not incur in any compression performance penalty regarding the more traditional predictive coding paradigm (at least for certain conditions). In the context of Wyner-Ziv video codecs, the so-called side information, which is a decoder estimate of the original frame to code, plays a critical role in the overall compression performance. For this reason, much research effort has been invested in the past decade to develop increasingly more efficient side information creation methods. This paper has the main objective to review and evaluate the available side information methods after proposing a classification taxonomy to guide this review, allowing to achieve more solid conclusions and better identify the next relevant research challenges. After classifying the side information creation methods into four classes, notably guess, try, hint and learn, the review of the most important techniques in each class and the evaluation of some of them leads to the important conclusion that the side information creation methods provide better rate-distortion (RD) performance depending on the amount of temporal correlation in each video sequence. It became also clear that the best available Wyner-Ziv video coding solutions are almost systematically based on the learn approach. The best solutions are already able to systematically outperform the H.264/AVC Intra, and also the H.264/AVC zero-motion standard solutions for specific types of content. (C) 2013 Elsevier B.V. All rights reserved.

Characteristics of motor resonance predict the pattern of flash-lag effects for biological motion

Background - When a moving stimulus and a briefly flashed static stimulus are physically aligned in space the static stimulus is perceived as lagging behind the moving stimulus. This vastly replicated phenomenon is known as the Flash-Lag Effect (FLE). For the first time we employed biological motion as the moving stimulus, which is important for two reasons. Firstly, biological motion is processed by visual as well as somatosensory brain areas, which makes it a prime candidate for elucidating the interplay between the two systems with respect to the FLE. Secondly, discussions about the mechanisms of the FLE tend to recur to evolutionary arguments, while most studies employ highly artificial stimuli with constant velocities. Methodology/Principal Finding - Since biological motion is ecologically valid it follows complex patterns with changing velocity. We therefore compared biological to symbolic motion with the same acceleration profile. Our results with 16 observers revealed a qualitatively different pattern for biological compared to symbolic motion and this pattern was predicted by the characteristics of motor resonance: The amount of anticipatory processing of perceived actions based on the induced perspective and agency modulated the FLE. Conclusions/Significance - Our study provides first evidence for an FLE with non-linear motion in general and with biological motion in particular. Our results suggest that predictive coding within the sensorimotor system alone cannot explain the FLE. Our findings are compatible with visual prediction (Nijhawan, 2008) which assumes that extrapolated motion representations within the visual system generate the FLE. These representations are modulated by sudden visual input (e.g. offset signals) or by input from other systems (e.g. sensorimotor) that can boost or attenuate overshooting representations in accordance with biased neural competition (Desimone & Duncan, 1995).

Applications of perceptual sparse representation (Spikegram) for copyright protection of audio signals

Chaque année, le piratage mondial de la musique coûte plusieurs milliards de dollars en pertes économiques, pertes d’emplois et pertes de gains des travailleurs ainsi que la perte de millions de dollars en recettes fiscales. La plupart du piratage de la musique est dû à la croissance rapide et à la facilité des technologies actuelles pour la copie, le partage, la manipulation et la distribution de données musicales [Domingo, 2015], [Siwek, 2007]. Le tatouage des signaux sonores a été proposé pour protéger les droit des auteurs et pour permettre la localisation des instants où le signal sonore a été falsifié. Dans cette thèse, nous proposons d’utiliser la représentation parcimonieuse bio-inspirée par graphe de décharges (spikegramme), pour concevoir une nouvelle méthode permettant la localisation de la falsification dans les signaux sonores. Aussi, une nouvelle méthode de protection du droit d’auteur. Finalement, une nouvelle attaque perceptuelle, en utilisant le spikegramme, pour attaquer des systèmes de tatouage sonore. Nous proposons tout d’abord une technique de localisation des falsifications (‘tampering’) des signaux sonores. Pour cela nous combinons une méthode à spectre étendu modifié (‘modified spread spectrum’, MSS) avec une représentation parcimonieuse. Nous utilisons une technique de poursuite perceptive adaptée (perceptual marching pursuit, PMP [Hossein Najaf-Zadeh, 2008]) pour générer une représentation parcimonieuse (spikegramme) du signal sonore d’entrée qui est invariante au décalage temporel [E. C. Smith, 2006] et qui prend en compte les phénomènes de masquage tels qu’ils sont observés en audition. Un code d’authentification est inséré à l’intérieur des coefficients de la représentation en spikegramme. Puis ceux-ci sont combinés aux seuils de masquage. Le signal tatoué est resynthétisé à partir des coefficients modifiés, et le signal ainsi obtenu est transmis au décodeur. Au décodeur, pour identifier un segment falsifié du signal sonore, les codes d’authentification de tous les segments intacts sont analysés. Si les codes ne peuvent être détectés correctement, on sait qu’alors le segment aura été falsifié. Nous proposons de tatouer selon le principe à spectre étendu (appelé MSS) afin d’obtenir une grande capacité en nombre de bits de tatouage introduits. Dans les situations où il y a désynchronisation entre le codeur et le décodeur, notre méthode permet quand même de détecter des pièces falsifiées. Par rapport à l’état de l’art, notre approche a le taux d’erreur le plus bas pour ce qui est de détecter les pièces falsifiées. Nous avons utilisé le test de l’opinion moyenne (‘MOS’) pour mesurer la qualité des systèmes tatoués. Nous évaluons la méthode de tatouage semi-fragile par le taux d’erreur (nombre de bits erronés divisé par tous les bits soumis) suite à plusieurs attaques. Les résultats confirment la supériorité de notre approche pour la localisation des pièces falsifiées dans les signaux sonores tout en préservant la qualité des signaux. Ensuite nous proposons une nouvelle technique pour la protection des signaux sonores. Cette technique est basée sur la représentation par spikegrammes des signaux sonores et utilise deux dictionnaires (TDA pour Two-Dictionary Approach). Le spikegramme est utilisé pour coder le signal hôte en utilisant un dictionnaire de filtres gammatones. Pour le tatouage, nous utilisons deux dictionnaires différents qui sont sélectionnés en fonction du bit d’entrée à tatouer et du contenu du signal. Notre approche trouve les gammatones appropriés (appelés noyaux de tatouage) sur la base de la valeur du bit à tatouer, et incorpore les bits de tatouage dans la phase des gammatones du tatouage. De plus, il est montré que la TDA est libre d’erreur dans le cas d’aucune situation d’attaque. Il est démontré que la décorrélation des noyaux de tatouage permet la conception d’une méthode de tatouage sonore très robuste. Les expériences ont montré la meilleure robustesse pour la méthode proposée lorsque le signal tatoué est corrompu par une compression MP3 à 32 kbits par seconde avec une charge utile de 56.5 bps par rapport à plusieurs techniques récentes. De plus nous avons étudié la robustesse du tatouage lorsque les nouveaux codec USAC (Unified Audion and Speech Coding) à 24kbps sont utilisés. La charge utile est alors comprise entre 5 et 15 bps. Finalement, nous utilisons les spikegrammes pour proposer trois nouvelles méthodes d’attaques. Nous les comparons aux méthodes récentes d’attaques telles que 32 kbps MP3 et 24 kbps USAC. Ces attaques comprennent l’attaque par PMP, l’attaque par bruit inaudible et l’attaque de remplacement parcimonieuse. Dans le cas de l’attaque par PMP, le signal de tatouage est représenté et resynthétisé avec un spikegramme. Dans le cas de l’attaque par bruit inaudible, celui-ci est généré et ajouté aux coefficients du spikegramme. Dans le cas de l’attaque de remplacement parcimonieuse, dans chaque segment du signal, les caractéristiques spectro-temporelles du signal (les décharges temporelles ;‘time spikes’) se trouvent en utilisant le spikegramme et les spikes temporelles et similaires sont remplacés par une autre. Pour comparer l’efficacité des attaques proposées, nous les comparons au décodeur du tatouage à spectre étendu. Il est démontré que l’attaque par remplacement parcimonieux réduit la corrélation normalisée du décodeur de spectre étendu avec un plus grand facteur par rapport à la situation où le décodeur de spectre étendu est attaqué par la transformation MP3 (32 kbps) et 24 kbps USAC.

Metallic Voice: Physiological and Acoustic Features

The metallic voice is usually confused with ring or nasality by singers and nontrained listeners. who are not used to perceptual vocal analysis. They believe a metallic voice results from a rise in fundamental frequency. A diagnostic error in this aspect may lead to lowering pitch, an incorrect procedure that Could Cause vocal overload and fatigue. The purpose of this article is to Study the quality of metallic voice considering the correlation between information of the physiological and acoustic plans, based on a perceptive consensual assumption. Fiberscopic video pharyngolaryngoscopy was performed on 21 professional singers while speaking vowel [e]-in normal and metallic modes to observe muscular movements and structural changes of the velopharynx, pharynx, and larynx. Vocal samples captured simultaneously to the fiberscopic examination were acoustically analyzed. Frequency and amplitude of the first four formants (F(1), F(2), F(3), and F(4)) were extracted by means of linear predictor coefficients (LPC) Spectrum and were statistically analyzed. Vocal tract adjustments such as velar lowering, pharyngeal wall narrowing, laryngeal rise, aryepiglottic, and lateral laryngeal constrictions were frequently found: there were no significant changes in frequency and amplitude of F(1) in the metallic voiced there were significant increases in amplitudes of F(2), F(3), and F(4) and in frequency for F, metallic Voice perceived as louder was correlated to an increase ill amplitude of F(3) and F(4). Physiological adjustments of velopharynx, pharynx, and larynx are combined in characterizing the metallic voice and can be acoustically related to changes in formant pattern.

Single-trial multisensory memories affect later auditory and visual object discrimination.

Multisensory memory traces established via single-trial exposures can impact subsequent visual object recognition. This impact appears to depend on the meaningfulness of the initial multisensory pairing, implying that multisensory exposures establish distinct object representations that are accessible during later unisensory processing. Multisensory contexts may be particularly effective in influencing auditory discrimination, given the purportedly inferior recognition memory in this sensory modality. The possibility of this generalization and the equivalence of effects when memory discrimination was being performed in the visual vs. auditory modality were at the focus of this study. First, we demonstrate that visual object discrimination is affected by the context of prior multisensory encounters, replicating and extending previous findings by controlling for the probability of multisensory contexts during initial as well as repeated object presentations. Second, we provide the first evidence that single-trial multisensory memories impact subsequent auditory object discrimination. Auditory object discrimination was enhanced when initial presentations entailed semantically congruent multisensory pairs and was impaired after semantically incongruent multisensory encounters, compared to sounds that had been encountered only in a unisensory manner. Third, the impact of single-trial multisensory memories upon unisensory object discrimination was greater when the task was performed in the auditory vs. visual modality. Fourth, there was no evidence for correlation between effects of past multisensory experiences on visual and auditory processing, suggestive of largely independent object processing mechanisms between modalities. We discuss these findings in terms of the conceptual short term memory (CSTM) model and predictive coding. Our results suggest differential recruitment and modulation of conceptual memory networks according to the sensory task at hand.

Nonlinear prediction based on score function

The linear prediction coding of speech is based in the assumption that the generation model is autoregresive. In this paper we propose a structure to cope with the nonlinear effects presents in the generation of the speech signal. This structure will consist of two stages, the first one will be a classical linear prediction filter, and the second one will model the residual signal by means of two nonlinearities between a linear filter. The coefficients of this filter are computed by means of a gradient search on the score function. This is done in order to deal with the fact that the probability distribution of the residual signal still is not gaussian. This fact is taken into account when the coefficients are computed by a ML estimate. The algorithm based on the minimization of a high-order statistics criterion, uses on-line estimation of the residue statistics and is based on blind deconvolution of Wiener systems [1]. Improvements in the experimental results with speech signals emphasize on the interest of this approach.