Integrating Computational Auditory Scene Analysis And Automatic Speech Recognition
Download Integrating Computational Auditory Scene Analysis And Automatic Speech Recognition PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Integrating Computational Auditory Scene Analysis And Automatic Speech Recognition book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Integrating Computational Auditory Scene Analysis and Automatic Speech Recognition
Abstract: Speech perception studies indicate that robustness of human speech recognition is primarily due to our ability to segregate a target sound source from other interferences. This perceptual process of auditory scene analysis (ASA) is of two types, primitive and schema-driven. This dissertation investigates several aspects of integrating computational ASA (CASA) and automatic speech recognition (ASR). While bottom-up CASA are used as front-end for ASR to improve its robustness, ASR is used to provide top-down information to enhance primitive segregation. Listeners are able to restore masked phonemes by utilizing lexical context. We present a schema-based model for phonemic restoration. The model employs missing-data ASR to decode masked speech and activates word templates via dynamic time warping. A systematic evaluation shows that the model restores both voiced and unvoiced phonemes with a high spectral quality. Missing-data ASR requires a binary mask from bottom-up CASA that identifies speech-dominant time-frequency regions of a noisy mixture. We propose a two-pass system that performs segregation and recognition in tandem. First, an n-best lattice, consistent with bottom-up speech separation, is generated. Second, the lattice is re-scored using a model-based hypothesis test to improve mask estimation and recognition accuracy concurrently. By combining CASA and ASR, we present a model that simulates listeners' ability to attend to a target speaker when degraded by energetic and informational masking. Missing-data ASR is used to account for energetic masking and the output degradation of CASA is used to model informational masking. The model successfully simulates several quantitative aspects of listener performance. The degradation in the output of CASA-based front-ends leads to uncertain ASR inputs. We estimate feature uncertainties in the spectral domain and transform them into the cepstral domain via nonlinear regression. The estimated uncertainty substantially improves recognition accuracy. We also investigate the effect of vocabulary size on conventional and missing-data ASRs. Based on binaural cues, for conventional ASR, we extract the speech signal using a Wiener filter and for missing-data ASR, we estimate a binary mask. We find that while missing-data ASR outperforms conventional ASR on a small vocabulary task, the relative performance reverses on a larger vocabulary task.
Computational Auditory Scene Analysis
The interest of AI in problems related to understanding sounds has a rich history dating back to the ARPA Speech Understanding Project in the 1970s. While a great deal has been learned from this and subsequent speech understanding research, the goal of building systems that can understand general acoustic signals--continuous speech and/or non-speech sounds--from unconstrained environments is still unrealized. Instead, there are now systems that understand "clean" speech well in relatively noiseless laboratory environments, but that break down in more realistic, noisier environments. As seen in the "cocktail-party effect," humans and other mammals have the ability to selectively attend to sound from a particular source, even when it is mixed with other sounds. Computers also need to be able to decide which parts of a mixed acoustic signal are relevant to a particular purpose--which part should be interpreted as speech, and which should be interpreted as a door closing, an air conditioner humming, or another person interrupting. Observations such as these have led a number of researchers to conclude that research on speech understanding and on nonspeech understanding need to be united within a more general framework. Researchers have also begun trying to understand computational auditory frameworks as parts of larger perception systems whose purpose is to give a computer integrated information about the real world. Inspiration for this work ranges from research on how different sensors can be integrated to models of how humans' auditory apparatus works in concert with vision, proprioception, etc. Representing some of the most advanced work on computers understanding speech, this collection of papers covers the work being done to integrate speech and nonspeech understanding in computer systems.
Techniques for Noise Robustness in Automatic Speech Recognition
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