[PDF] A Study Of Adaptive Enhancement Methods For Improved Distant Speech Recognition eBook
A Study Of Adaptive Enhancement Methods For Improved Distant Speech Recognition Book in PDF, ePub and Kindle version is available to download in english. Read online anytime anywhere directly from your device. Click on the download button below to get a free pdf file of A Study Of Adaptive Enhancement Methods For Improved Distant Speech Recognition book. This book definitely worth reading, it is an incredibly well-written.
Automatic speech recognition systems trained on speech data recorded by microphones placed close to the speaker tend to perform poorly on speech recorded by microphones placed farther away from the speaker due to reverberation effects and background noise. I designed and implemented a variety of machine learning models to improve distant speech recognition performance by adaptively enhancing incoming speech to appear as if it was recorded in a close-talking environment, regardless of whether it was originally recorded in a close-talking or distant environment. These were evaluated by passing the enhanced speech to acoustic models trained on only close-talking speech and comparing error rates to those achieved without speech enhancement. Experiments conducted on the AMI, TIMIT and TED-LIUM datasets indicate that decreases in error rate on distant speech of up to 33% relative can be achieved by these with only minor increases (1% relative) on clean speech.
A complete overview of distant automatic speech recognition The performance of conventional Automatic Speech Recognition (ASR) systems degrades dramatically as soon as the microphone is moved away from the mouth of the speaker. This is due to a broad variety of effects such as background noise, overlapping speech from other speakers, and reverberation. While traditional ASR systems underperform for speech captured with far-field sensors, there are a number of novel techniques within the recognition system as well as techniques developed in other areas of signal processing that can mitigate the deleterious effects of noise and reverberation, as well as separating speech from overlapping speakers. Distant Speech Recognitionpresents a contemporary and comprehensive description of both theoretic abstraction and practical issues inherent in the distant ASR problem. Key Features: Covers the entire topic of distant ASR and offers practical solutions to overcome the problems related to it Provides documentation and sample scripts to enable readers to construct state-of-the-art distant speech recognition systems Gives relevant background information in acoustics and filter techniques, Explains the extraction and enhancement of classification relevant speech features Describes maximum likelihood as well as discriminative parameter estimation, and maximum likelihood normalization techniques Discusses the use of multi-microphone configurations for speaker tracking and channel combination Presents several applications of the methods and technologies described in this book Accompanying website with open source software and tools to construct state-of-the-art distant speech recognition systems This reference will be an invaluable resource for researchers, developers, engineers and other professionals, as well as advanced students in speech technology, signal processing, acoustics, statistics and artificial intelligence fields.
This book covers the state-of-the-art in deep neural-network-based methods for noise robustness in distant speech recognition applications. It provides insights and detailed descriptions of some of the new concepts and key technologies in the field, including novel architectures for speech enhancement, microphone arrays, robust features, acoustic model adaptation, training data augmentation, and training criteria. The contributed chapters also include descriptions of real-world applications, benchmark tools and datasets widely used in the field. This book is intended for researchers and practitioners working in the field of speech processing and recognition who are interested in the latest deep learning techniques for noise robustness. It will also be of interest to graduate students in electrical engineering or computer science, who will find it a useful guide to this field of research.
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
With the proliferation of mobile devices and hearing devices, including hearing aids and cochlear implants, there is a growing and pressing need to design algorithms that can improve speech intelligibility without sacrificing quality. Responding to this need, Speech Enhancement: Theory and Practice, Second Edition introduces readers to the basic pr
In recent years, there has been a significant increase in the popularity of voice-enabled technologies which use human speech as the primary interface with machines. Recent advancements in acoustic modeling and feature design have increased the accuracy of Automatic Speech Recognition (ASR) to levels that enable voice interfaces to be used in many applications. However, much of the current performance is dependent on the use of close-talking microphones, (i.e., scenarios in which the user speaks directly into a hand-held or body-worn microphone). There is still a rather large performance gap experienced in distant-talking scenarios in which speech is recorded by far-field microphones that are placed at a distance from the speaker. In such scenarios, the distorting effects of distance (such as room reverberation and environment noise) make the recognition task significantly more challenging. In this dissertation, we propose novel approaches for designing a distant-talking ASR front-end as well as training robust acoustic models to reduce the existing gap between far-field and close-talking ASR performance. Specifically, we i) propose a novel multi-channel front-end enhancement algorithm for improved ASR in reverberant rooms using distributed non-uniform microphone arrays with random unknown locations; ii) propose a novel neural network model training approach using adversarial training to improve the robustness of multi-condition acoustic models that are trained directly on far-field data; iii) study alternate neural network adaptation strategies for far-field adaptation to the acoustic properties of specific target environments. Experimental results are provided based on far-field benchmark tasks and datasets which demonstrate the effectiveness of the proposed approaches for increasing far-field robustness in ASR. Based on experiments using reverberated TIMIT sentences, the proposed multi-channel front-end provides WER improvements of +21.5% and +37.7% in two-channel and four-channel scenarios over a single-channel scenario in which the channel with best signal quality is selected. On the acoustic modeling side and based on results of experiments on AMI corpus, the proposed multi-domain training approach provides a relative character error rate reduction of +3.3% with respect to a conventional multi-condition trained baseline, and +25.4% with respect to a clean-trained baseline.
Speech enhancement is a classical problem in signal processing, yet still largely unsolved. Two of the conventional approaches for solving this problem are linear filtering, like the classical Wiener filter, and subspace methods. These approaches have traditionally been treated as different classes of methods and have been introduced in somewhat different contexts. Linear filtering methods originate in stochastic processes, while subspace methods have largely been based on developments in numerical linear algebra and matrix approximation theory. This book bridges the gap between these two classes of methods by showing how the ideas behind subspace methods can be incorporated into traditional linear filtering. In the context of subspace methods, the enhancement problem can then be seen as a classical linear filter design problem. This means that various solutions can more easily be compared and their performance bounded and assessed in terms of noise reduction and speech distortion. The book shows how various filter designs can be obtained in this framework, including the maximum SNR, Wiener, LCMV, and MVDR filters, and how these can be applied in various contexts, like in single-channel and multichannel speech enhancement, and in both the time and frequency domains. First short book treating subspace approaches in a unified way for time and frequency domains, single-channel, multichannel, as well as binaural, speech enhancement Bridges the gap between optimal filtering methods and subspace approaches Includes original presentation of subspace methods from different perspectives
Speech enhancement has been extensively studied for many years and various speech enhancement methods have been developed during the past decades. One of the objectives of speech enhancement is to provide high-quality speech communication in the presence of background noise and concurrent interference signals. In the process of speech communication, the clean speech sig- nal is inevitably corrupted by acoustic noise from the surrounding environment, transmission media, communication equipment, electrical noise, other speakers, and other sources of interference. These disturbances can significantly degrade the quality and intelligibility of the received speech signal. Therefore, it is of great interest to develop efficient speech enhancement techniques to recover the original speech from the noisy observation. In recent years, various techniques have been developed to tackle this problem, which can be classified into single channel and multi-channel enhancement approaches. Since single channel enhancement is easy to implement, it has been a significant field of research and various approaches have been developed. For example, spectral subtraction and Wiener filtering, are among the earliest single channel methods, which are based on estimation of the power spectrum of stationary noise. However, when the noise is non-stationary, or there exists music noise and ambient speech noise, the enhancement performance would degrade considerably. To overcome this disadvantage, this thesis focuses on single channel speech enhancement under adverse noise environment, especially the non-stationary noise environment. Recently, wavelet transform based methods have been widely used to reduce the undesired background noise. On the other hand, the Kalman filter (KF) methods offer competitive denoising results, especially in non-stationary environment. It has been used as a popular and powerful tool for speech enhancement during the past decades. In this regard, a single channel wavelet thresholding based Kalman filter (KF) algorithm is proposed for speech enhancement in this thesis. The wavelet packet (WP) transform is first applied to the noise corrupted speech on a frame-by-frame basis, which decomposes each frame into a number of subbands. A voice activity detector (VAD) is then designed to detect the voiced/unvoiced frames of the subband speech. Based on the VAD result, an adaptive thresholding scheme is applied to each subband speech followed by the WP based reconstruction to obtain the pre-enhanced speech. To achieve a further level of enhancement, an iterative Kalman filter (IKF) is used to process the pre-enhanced speech. The proposed adaptive thresholding iterative Kalman filtering (AT-IKF) method is evaluated and compared with some existing methods under various noise conditions in terms of segmental SNR and perceptual evaluation of speech quality (PESQ) as two well-known performance indexes. Firstly, we compare the proposed adaptive thresholding (AT) scheme with three other threshold- ing schemes: the non-linear universal thresholding (U-T), the non-linear wavelet packet transform thresholding (WPT-T) and the non-linear SURE thresholding (SURE-T). The experimental results show that the proposed AT scheme can significantly improve the segmental SNR and PESQ for all input SNRs compared with the other existing thresholding schemes. Secondly, extensive computer simulations are conducted to evaluate the proposed AT-IKF as opposed to the AT and the IKF as standalone speech enhancement methods. It is shown that the AT-IKF method still performs the best. Lastly, the proposed ATIKF method is compared with three representative and popular meth- ods: the improved spectral subtraction based speech enhancement algorithm (ISS), the improved Wiener filter based method (IWF) and the representative subband Kalman filter based algorithm (SIKF). Experimental results demonstrate the effectiveness of the proposed method as compared to some previous works both in terms of segmental SNR and PESQ.
Real World Speech Processing brings together in one place important contributions and up-to-date research results in this fast-moving area. The contributors to this work were selected from the leading researchers and practitioners in this field. The work, originally published as Volume 36, Numbers 2-3 of the Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, will be valuable to anyone working or researching in the field of speech processing. It serves as an excellent reference, providing insight into some of the most challenging issues being examined today.