"The performance of an automatic speech recognition (ASR) system degrades dramatically when speech is corrupted by background noise. In many ASR applications, however, the presence of the background noise is unavoidable. Feature representations in ASR are usually derived from the short-time spectral magnitude of the speech signal, known as the speech spectrogram. The goal of the work in this thesis is to develop noise robust ASR systems by reconstructing noise corrupted speech spectrograms. This is addressed as a data imputation problem within the framework of missing feature theory in computational auditory scene analysis. This thesis presents a number of data imputation techniques which can add noise robustness to an ASR system while making minimum assumptions about the characteristics of the background noise. There are three major contributions in this thesis work. The first relates to the spectrographic mask estimation which is performed to identify noise corrupted features. Having identified the noise corrupted speech features, a spectrogram reconstruction technique is employed to estimate the underlying clean features and reconstruct the noise corrupted features. A mask estimation method, based on speech enhancement techniques presented previously in the literature, is incorporated in a spectrogram reconstruction approach for noise robust ASR. The presented mask estimation technique is shown to perform well both in stationary and non-stationary noisy environments. More importantly, this technique does not require any prior knowledge of the background noise type or the SNR level.The second contribution of this thesis is a filterbank based approach to spectrogram reconstruction based on discrete wavelet transform (DWT) de-noising. In these techniques, speech spectrogram coefficients are input to a DWT filterbank. Most of the spectrogram reconstruction approaches presented in the literature are model-based techniques that can only provide accurate estimates of the underlying clean speech when the characteristics of the noise corrupted features do not deviate from those of the model. Discrete wavelet transform (DWT) based de-noising methods have been used for signal reconstruction, but often require that the background noise is stationary and modeled by a Gaussian distribution. A novel approach is presented in this thesis for incorporating the information derived from spectrographic masks in a DWT-based de-noising method. It will be shown that the proposed approach reduces the impact of model mismatch associated with parametric approaches and exploits the robustness of non-parametric wavelet de-noising approach. This technique, however, can perform at its best only if some parameters are tuned to the noise conditions. The third contribution of this thesis is a procedure which combines multiple DWT-based reconstructed spectral features using a closed loop optimization algorithm which is related to the overall performance of the ASR system. The feature channels are formed from an ensemble of reconstructed spectrograms generated by applyingDWT-based spectrogram reconstruction with multiple parameter settings. The spectrograms associated with these feature channels differ in the degreeto which spectral information is suppressed across multiple scales and frequencybands.A consistent increase in word accuracy is reported for this multi-channelperformance monitoring approach with respect to animplementation of a more well known minimum mean squared error approach formissing feature based spectrogram reconstruction. " --

Automatic speech recognition suffers from a lack of robustness with respect to noise, reverberation and interfering speech. The growing field of speech recognition in the presence of missing or uncertain input data seeks to ameliorate those problems by using not only a preprocessed speech signal but also an estimate of its reliability to selectively focus on those segments and features that are most reliable for recognition. This book presents the state of the art in recognition in the presence of uncertainty, offering examples that utilize uncertainty information for noise robustness, reverberation robustness, simultaneous recognition of multiple speech signals, and audiovisual speech recognition. The book is appropriate for scientists and researchers in the field of speech recognition who will find an overview of the state of the art in robust speech recognition, professionals working in speech recognition who will find strategies for improving recognition results in various conditions of mismatch, and lecturers of advanced courses on speech processing or speech recognition who will find a reference and a comprehensive introduction to the field. The book assumes an understanding of the fundamentals of speech recognition using Hidden Markov Models.

Automatic speech recognition (ASR) systems are finding increasing use in everyday life. Many of the commonplace environments where the systems are used are noisy, for example users calling up a voice search system from a busy cafeteria or a street. This can result in degraded speech recordings and adversely affect the performance of speech recognition systems. As the use of ASR systems increases, knowledge of the state-of-the-art in techniques to deal with such problems becomes critical to system and application engineers and researchers who work with or on ASR technologies. This book presents a comprehensive survey of the state-of-the-art in techniques used to improve the robustness of speech recognition systems to these degrading external influences. Key features: Reviews all the main noise robust ASR approaches, including signal separation, voice activity detection, robust feature extraction, model compensation and adaptation, missing data techniques and recognition of reverberant speech. Acts as a timely exposition of the topic in light of more widespread use in the future of ASR technology in challenging environments. Addresses robustness issues and signal degradation which are both key requirements for practitioners of ASR. Includes contributions from top ASR researchers from leading research units in the field

Noise and distortion that degrade the quality of speech signals can come from any number of sources. The technology and techniques for dealing with noise are almost as numerous, but it is only recently, with the development of inexpensive digital signal processing hardware, that the implementation of the technology has become practical. Noise Reduction in Speech Applications provides a comprehensive introduction to modern techniques for removing or reducing background noise from a range of speech-related applications. Self-contained, it starts with a tutorial-style chapter of background material, then focuses on system aspects, digital algorithms, and implementation. The final section explores a variety of applications and demonstrates to potential users of the technology the results possible with the noise reduction techniques presented. The book offers chapters contributed by international experts, a practical, systems approach, and numerous references. For electrical, acoustics, signal processing, communications, and bioengineers, Noise Reduction in Speech Applications is a valuable resource that shows you how to decide whether noise reduction will solve problems in your own systems and how to make the best use of the technologies available.

This book constitutes the proceedings of the 10th International Conference on Latent Variable Analysis and Signal Separation, LVA/ICA 2012, held in Tel Aviv, Israel, in March 2012. The 20 revised full papers presented together with 42 revised poster papers, 1 keynote lecture, and 2 overview papers for the regular, as well as for the special session were carefully reviewed and selected from numerous submissions. Topics addressed are ranging from theoretical issues such as causality analysis and measures, through novel methods for employing the well-established concepts of sparsity and non-negativity for matrix and tensor factorization, down to a variety of related applications ranging from audio and biomedical signals to precipitation analysis.

The refereed proceedings of the 6th International Workshop on Computational Processing of the Portuguese Language, PROPOR 2003, held in Faro, Portugal, in June 2003. The 24 revised full papers and 17 revised short papers presented were carefully reviewed and selected from 64 submissions. The papers are organized in topical sections on speech analysis and recognition; speech synthesis; pragmatics, discourse, semantics, syntax, and the lexicon; tools, resources, and applications; dialogue systems; summarization and information extraction; and evaluation.