Kernelized log linear models for continuous speech recognition

Large margin criteria and discriminative models are two effective improvements for HMM-based speech recognition. This paper proposed a large margin trained log linear model with kernels for CSR. To avoid explicitly computing in the high dimensional feature space and to achieve the nonlinear decision boundaries, a kernel based training and decoding framework is proposed in this work. To make the system robust to noise a kernel adaptation scheme is also presented. Previous work in this area is extended in two directions. First, most kernels for CSR focus on measuring the similarity between two observation sequences. The proposed joint kernels defined a similarity between two observation-label sequence pairs on the sentence level. Second, this paper addresses how to efficiently employ kernels in large margin training and decoding with lattices. To the best of our knowledge, this is the first attempt at using large margin kernel-based log linear models for CSR. The model is evaluated on a noise corrupted continuous digit task: AURORA 2.0. © 2013 IEEE.

Models of Noise and Robust Estimates

Given n noisy observations g; of the same quantity f, it is common use to give an estimate of f by minimizing the function Eni=1(gi-f)2. From a statistical point of view this corresponds to computing the Maximum likelihood estimate, under the assumption of Gaussian noise. However, it is well known that this choice leads to results that are very sensitive to the presence of outliers in the data. For this reason it has been proposed to minimize the functions of the form Eni=1V(gi-f), where V is a function that increases less rapidly than the square. Several choices for V have been proposed and successfully used to obtain "robust" estimates. In this paper we show that, for a class of functions V, using these robust estimators corresponds to assuming that data are corrupted by Gaussian noise whose variance fluctuates according to some given probability distribution, that uniquely determines the shape of V.

Improving ICP with Easy Implementation for Free Form Surface Matching

Liu, Yonghuai. Improving ICP with Easy Implementation for Free Form Surface Matching. Pattern Recognition, vol. 37, no. 2, pp. 211-226, 2004.

Echoes of existentialism in the works of Carlos Fuentes

In this thesis I have set out to trace the echoes of existentialism in the work of the Mexican novelist, Carlos Fuentes scrutinizing, in particular, La región más transparente, La muerte de Artemio Cruz and Cambio de piel. In the opening segment of the thesis I outline the essential tenets of existentialist thought and how it became the predominant philosophical and literary movement of the early part of the twentieth-century. Stemming from the work of Sören Kierkegaard in Denmark towards the end of the nineteenth-century, it challenged the arid philosophies of previous generations and provided a new way of looking at man and the human condition. In this opening chapter, I study the works of the more important philosophers in this regard such as Heidegger, Sartre, Jaspers, Marcel, Unamuno, and Ortega y Gasset and show how each in his own way contributed to the further development of the new philosophy. Chapter 2 is concerned with the spread of existentialism to the Latin American continent. In the early part of the twentieth-century, Mexico was emerging from a turbulent revolutionary period and seeking a solution to the fractured nature of its society. The Spanish philosopher, Ortega y Gasset, and the many Spanish intellectuals who sought refuge from Franco’s dictatorship in Mexico, helped to popularise the new philosophy and these lively debates about existentialism served to underpin ideas around mexicanidad or Mexican national identity. Carlos Fuentes was deeply immersed in the debate of his time, positioned as he was as a prominent public intellectual. In La muerte de Artemio Cruz he shows us how great wealth and power are a poor recompense for the loss of love and compassion and lead only to alienation and selfishness. In his other best known novel, La región más transparente, he explores the rise of modern Mexico and its society – an inauthentic society that is corrupted by a scramble for wealth and self-aggrandizement. The final chapter is devoted to the study of Cambio de piel which is concerned with violence and alienation as central pillars of existence. The violence depicted here precipitates a crisis in the human condition and an accompanying sense of alienation. The thesis seeks to establish that existentialism is central not only to Fuentes’s literary concerns but also forms a part of his ethics as an artist.

Speech Recognition with unknown partial feature corruption - a review of the union model

This paper provides a summary of our studies on robust speech recognition based on a new statistical approach – the probabilistic union model. We consider speech recognition given that part of the acoustic features may be corrupted by noise. The union model is a method for basing the recognition on the clean part of the features, thereby reducing the effect of the noise on recognition. To this end, the union model is similar to the missing feature method. However, the two methods achieve this end through different routes. The missing feature method usually requires the identity of the noisy data for noise removal, while the union model combines the local features based on the union of random events, to reduce the dependence of the model on information about the noise. We previously investigated the applications of the union model to speech recognition involving unknown partial corruption in frequency band, in time duration, and in feature streams. Additionally, a combination of the union model with conventional noise-reduction techniques was studied, as a means of dealing with a mixture of known or trainable noise and unknown unexpected noise. In this paper, a unified review, in the context of dealing with unknown partial feature corruption, is provided into each of these applications, giving the appropriate theory and implementation algorithms, along with an experimental evaluation.

Robust Speaker Recognition in Noisy Conditions

This paper investigates the problem of speaker identi-fication and verification in noisy conditions, assuming that speechsignals are corrupted by environmental noise, but knowledgeabout the noise characteristics is not available. This research ismotivated in part by the potential application of speaker recog-nition technologies on handheld devices or the Internet. Whilethe technologies promise an additional biometric layer of securityto protect the user, the practical implementation of such systemsfaces many challenges. One of these is environmental noise. Due tothe mobile nature of such systems, the noise sources can be highlytime-varying and potentially unknown. This raises the require-ment for noise robustness in the absence of information about thenoise. This paper describes a method that combines multicondi-tion model training and missing-feature theory to model noisewith unknown temporal-spectral characteristics. Multiconditiontraining is conducted using simulated noisy data with limitednoise variation, providing a “coarse” compensation for the noise,and missing-feature theory is applied to refine the compensationby ignoring noise variation outside the given training conditions,thereby reducing the training and testing mismatch. This paperis focused on several issues relating to the implementation of thenew model for real-world applications. These include the gener-ation of multicondition training data to model noisy speech, thecombination of different training data to optimize the recognitionperformance, and the reduction of the model’s complexity. Thenew algorithm was tested using two databases with simulated andrealistic noisy speech data. The first database is a redevelopmentof the TIMIT database by rerecording the data in the presence ofvarious noise types, used to test the model for speaker identifica-tion with a focus on the varieties of noise. The second database isa handheld-device database collected in realistic noisy conditions,used to further validate the model for real-world speaker verifica-tion. The new model is compared to baseline systems and is foundto achieve lower error rates.

A novel shrinkage technique based on the normal inverse Gaussian density model

This paper proposes a novel image denoising technique based on the normal inverse Gaussian (NIG) density model using an extended non-negative sparse coding (NNSC) algorithm proposed by us. This algorithm can converge to feature basis vectors, which behave in the locality and orientation in spatial and frequency domain. Here, we demonstrate that the NIG density provides a very good fitness to the non-negative sparse data. In the denoising process, by exploiting a NIG-based maximum a posteriori estimator (MAP) of an image corrupted by additive Gaussian noise, the noise can be reduced successfully. This shrinkage technique, also referred to as the NNSC shrinkage technique, is self-adaptive to the statistical properties of image data. This denoising method is evaluated by values of the normalized signal to noise rate (SNR). Experimental results show that the NNSC shrinkage approach is indeed efficient and effective in denoising. Otherwise, we also compare the effectiveness of the NNSC shrinkage method with methods of standard sparse coding shrinkage, wavelet-based shrinkage and the Wiener filter. The simulation results show that our method outperforms the three kinds of denoising approaches mentioned above.

The symbolization of central approximants in the IPA

Approximants that can be considered weaker versions of voiced fricatives (termed here ‘frictionless continuants’) are poorly served by the IPA in terms of symbolization as compared to semi-vowel approximants. In this paper we survey the central approximants and the symbols and diacritics used to transcribe them; we focus on evidence for the use of non-rhotic frictionless continuants in both natural language (by which we mean non-clinical varieties) and disordered speech; and we suggest some possible unitary symbols for those that currently require the use of a hard-to-read lowering diacritic beneath the symbol for the corresponding voiced fricative.

Methodology for Validating Artifact Removal Techniques for Physiological Signals

Artifact removal from physiological signals is an essential component of the biosignal processing pipeline. The need for powerful and robust methods for this process has become particularly acute as healthcare technology deployment undergoes transition from the current hospital-centric setting toward a wearable and ubiquitous monitoring environment. Currently, determining the relative efficacy and performance of the multiple artifact removal techniques available on real world data can be problematic, due to incomplete information on the uncorrupted desired signal. The majority of techniques are presently evaluated using simulated data, and therefore, the quality of the conclusions is contingent on the fidelity of the model used. Consequently, in the biomedical signal processing community, there is considerable focus on the generation and validation of appropriate signal models for use in artifact suppression. Most approaches rely on mathematical models which capture suitable approximations to the signal dynamics or underlying physiology and, therefore, introduce some uncertainty to subsequent predictions of algorithm performance. This paper describes a more empirical approach to the modeling of the desired signal that we demonstrate for functional brain monitoring tasks which allows for the procurement of a ground truth signal which is highly correlated to a true desired signal that has been contaminated with artifacts. The availability of this ground truth, together with the corrupted signal, can then aid in determining the efficacy of selected artifact removal techniques. A number of commonly implemented artifact removal techniques were evaluated using the described methodology to validate the proposed novel test platform. © 2012 IEEE.

Robust Audio-Visual Speech Recognition under Noisy Audio-Video Conditions

This paper presents the maximum weighted stream posterior (MWSP) model as a robust and efficient stream integration method for audio-visual speech recognition in environments, where the audio or video streams may be subjected to unknown and time-varying corruption. A significant advantage of MWSP is that it does not require any specific measurements of the signal in either stream to calculate appropriate stream weights during recognition, and as such it is modality-independent. This also means that MWSP complements and can be used alongside many of the other approaches that have been proposed in the literature for this problem. For evaluation we used the large XM2VTS database for speaker-independent audio-visual speech recognition. The extensive tests include both clean and corrupted utterances with corruption added in either/both the video and audio streams using a variety of types (e.g., MPEG-4 video compression) and levels of noise. The experiments show that this approach gives excellent performance in comparison to another well-known dynamic stream weighting approach and also compared to any fixed-weighted integration approach in both clean conditions or when noise is added to either stream. Furthermore, our experiments show that the MWSP approach dynamically selects suitable integration weights on a frame-by-frame basis according to the level of noise in the streams and also according to the naturally fluctuating relative reliability of the modalities even in clean conditions. The MWSP approach is shown to maintain robust recognition performance in all tested conditions, while requiring no prior knowledge about the type or level of noise.

Robust Multimodal Person Identification With Limited Training Data

This paper presents a novel method of audio-visual feature-level fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there are limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new multimodal feature representation and a modified cosine similarity are introduced to combine and compare bimodal features with limited training data, as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal dataset created from the SPIDRE speaker recognition database and AR face recognition database with variable noise corruption of speech and occlusion in the face images. The system's speaker identification performance on the SPIDRE database, and facial identification performance on the AR database, is comparable with the literature. Combining both modalities using the new method of multimodal fusion leads to significantly improved accuracy over the unimodal systems, even when both modalities have been corrupted. The new method also shows improved identification accuracy compared with the bimodal systems based on multicondition model training or missing-feature decoding alone.

Combining multi-band and frequency-filtering techniques for speech recognition in noisy environments

While current speech recognisers give acceptable performance in carefully controlled environments, their performance degrades rapidly when they are applied in more realistic situations. Generally, the environmental noise may be classified into two classes: the wide-band noise and narrow band noise. While the multi-band model has been shown to be capable of dealing with speech corrupted by narrow-band noise, it is ineffective for wide-band noise. In this paper, we suggest a combination of the frequency-filtering technique with the probabilistic union model in the multi-band approach. The new system has been tested on the TIDIGITS database, corrupted by white noise, noise collected from a railway station, and narrow-band noise, respectively. The results have shown that this approach is capable of dealing with noise of narrow-band or wide-band characteristics, assuming no knowledge about the noisy environment.

Robust bimodal person identification using face and speech with limited training data and corruption of both modalities

This paper presents a novel method of audio-visual fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there is a limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new representation and a modified cosine similarity are introduced for combining and comparing bimodal features with limited training data as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal data set created from the SPIDRE and AR databases with variable noise corruption of speech and occlusion in the face images. The new method has demonstrated improved recognition accuracy.

Statistical data correction for unreliable memories

In this paper, we introduce a statistical data-correction framework that aims at improving the DSP system performance in presence of unreliable memories. The proposed signal processing framework implements best-effort error mitigation for signals that are corrupted by defects in unreliable storage arrays using a statistical correction function extracted from the signal statistics, a data-corruption model, and an application-specific cost function. An application example to communication systems demonstrates the efficacy of the proposed approach.

Largest Matching Areas for Illumination and Occlusion Robust Face Recognition

In this paper, we introduce a novel approach to face recognition which simultaneously tackles three combined challenges: 1) uneven illumination; 2) partial occlusion; and 3) limited training data. The new approach performs lighting normalization, occlusion de-emphasis and finally face recognition, based on finding the largest matching area (LMA) at each point on the face, as opposed to traditional fixed-size local area-based approaches. Robustness is achieved with novel approaches for feature extraction, LMA-based face image comparison and unseen data modeling. On the extended YaleB and AR face databases for face identification, our method using only a single training image per person, outperforms other methods using a single training image, and matches or exceeds methods which require multiple training images. On the labeled faces in the wild face verification database, our method outperforms comparable unsupervised methods. We also show that the new method performs competitively even when the training images are corrupted.