單麥克風語音分離的目標是從一個語音混合 (speech mixture) 中重建兩個或更多的語音源 (source)。這技術可作為語音應用的前置處理，例如從多媒體音軌中抽取資訊。雖然作為欠定 (under-determined) 語音分離的極端例子，基本上沒可能確切地還原語音源，但透過語音源的統計模型，仍可重構出最有可能的語音源。 / 語音分離的性能藉著圖模式 (graphical modeling) 的應用而得以提升。本論文比較了因子隱馬爾可夫模型(factorial Hidden Markov Model (HMM) )的精確算法和近似算法的複雜度和對語音分離性能的影響，並且調查語音源統計模型中的狀態轉移機率 (state transition probabilities) 對語音分離性能的影響。 / 統計模型錯配在語音分離中時有發生。有限的訓練資料和使用有限的狀態空間 (acoustic states) 對語音源建模都會導致錯配。本論文研究了使用條件隨機域 (conditional random field (CRF) ) 來對語音源狀態空間的後驗概率直接建模。計算語音源的最小均方差估計 (minimum mean-square error)時，這後驗概率是必須的。條件隨機域是一種判別模型 (discriminative model)，比生成模型 (generative model) 例如隱馬爾可夫模型對模型錯配有更高的耐受性。使用大間隔 (large-margin) 參數估計更進一步提升語音分離的效能。 / 實驗結果證明當不同語音源的功率比 (signal-to-signal ratio) 相近時，使用條件隨機域作語音分離可以獲得更好的語音音質客觀測量參數(objective quality measures) 和語音識別結果。即使使用簡化了的條件隨機域，結果仍和使用因子隱馬爾可夫模型相當。 / Single-microphone speech separation requires to reconstruct two or more sources from only one speech mixture. It can serve as the front-end for speech applications that demand for robustness against interfering signals, such as information extraction from sound streams of multimedia. As an extreme case of under-determined source separation problem, a unique solution for source reconstruction is unlikely to be achieved, but the most probable source observations can be obtained through statistical inference given their prior information in a statistical model-based setting. / The performance of statistical model-based methods has been progressively improved by the use of graphical models to organize the prior information. In this thesis, the performance of the exact and the approximated statistical inference algorithms on single-microphone speech separation with factorial Hidden Markov models (HMM) are evaluated in terms of speech quality and computational complexity. The important role of state transitions in the source models is also investigated. / Model mis-specification is a major problem in model-based speech separation. These mis-specifications are caused by various factors, including limited amount of training data and finite number of acoustic states. Compared with generative approach such as factorial HMM, direct models like conditional random fields (CRF) are considered to be more robust to model mis-specification due to the inherent discrimination ability. In this thesis, the application of conditional random field (CRF) for single-microphone speech separation is investigated. The posterior probabilities of acoustic states given the mixture, which are essential to minimum mean-square error estimation of the sources, are modeled in a maximum entropy probability distribution. The performance of CRF formulations is further improved with a largemargin approach of parameter estimation. / Experimental results confirm that CRF formulations achieve the improved objective quality measures and automatic speech recognition accuracy of the reconstructed sources, especially when the sources are competing with similar signal-to-signal ratio. Even with a simplified CRF formulation, the performance is still comparable to factorial HMM. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Yeung, Yu Ting. / Thesis (Ph.D.) Chinese University of Hong Kong, 2014. / Includes bibliographical references (leaves 102-118). / Abstracts also in Chinese.

In this dissertation, through three separately published articles, I interrogate the role of expert knowledge in First Amendment theory and doctrine. I argue that expert knowledge ought to play a prominent role in answering doctrinally relevant empirical questions, as in the case of incorporating a scientifically grounded understanding of visual perception into Establishment Clause inquiries concerning religious symbols. Moreover, the generation and dissemination of expert knowledge itself is worthy of First Amendment protection, for example in protecting professional speech. And expert knowledge should determine the scope of First Amendment protection for professional advice. There is, in other words, a close but often underappreciated connection between expert knowledge and the First Amendment. In Active Symbols, I challenge the assumption sometimes articulated in Establishment Clause case law involving religious symbols that visual representations of religious symbols are merely “passive” as compared to textual (spoken or written) religious references. Drawing on one relevant body of expert knowledge—cognitive neuroscience—I argue that images are at least as “active” as text. The lack of judicial expertise on the empirical question of how visual images, as opposed to spoken or written words, communicate has led to a distortion in the development of Establishment Clause doctrine. This distortion can be remedied by taking relevant expert knowledge into consideration where such knowledge can answer germane empirical questions that are doctrinally relevant but tend to be outside the realm of judicial expertise. Professional Speech argues that the First Amendment protects the communication of expert knowledge by a professional to a client-within a professional-client relationship for the purpose of giving professional advice. The First Amendment thus provides a shield against state interference that seeks to prescribe or alter the content of professional speech. The key to understanding professional speech, I suggest, lies in the concept of the learned professions as knowledge communities. First Amendment protection for professional speech can be justified on all traditional grounds: autonomy interests of the speaker and listener, marketplace interests, and democratic self-government. Unprofessional Advice provides a theory to identify the range of valid professional advice for First Amendment purposes. Building on the concept of the professions as knowledge communities, this article explores the range of professional advice that may be given consistent with the professional knowledge community’s common ways of knowing and reasoning and the respective profession’s agreed upon methodology. Because knowledge communities are not monolithic, there is a range of knowledge that is accepted as good professional advice. Advice falling within this range should receive robust First Amendment protection. Advice not within this range, however, is subject to malpractice liability, and the First Amendment provides no defense.

Wang, Ning. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (leaves 106-115). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Introduction to Speech and Speaker Recognition --- p.1 / Chapter 1.2 --- Difficulties and Challenges of Speaker Authentication --- p.6 / Chapter 1.3 --- Objectives and Thesis Outline --- p.7 / Chapter 2 --- Speaker Recognition System --- p.10 / Chapter 2.1 --- Baseline Speaker Recognition System Overview --- p.10 / Chapter 2.1.1 --- Feature Extraction --- p.12 / Chapter 2.1.2 --- Pattern Generation and Classification --- p.24 / Chapter 2.2 --- Performance Evaluation Metric for Different Speaker Recognition Tasks --- p.30 / Chapter 2.3 --- Robustness of Speaker Recognition System --- p.30 / Chapter 2.3.1 --- Speech Corpus: CU2C --- p.30 / Chapter 2.3.2 --- Noise Database: NOISEX-92 --- p.34 / Chapter 2.3.3 --- Mismatched Training and Testing Conditions --- p.35 / Chapter 2.4 --- Summary --- p.37 / Chapter 3 --- Speaker Recognition System using both Vocal Tract and Vocal Source Features --- p.38 / Chapter 3.1 --- Speech Production Mechanism --- p.39 / Chapter 3.1.1 --- Speech Production: An Overview --- p.39 / Chapter 3.1.2 --- Acoustic Properties of Human Speech --- p.40 / Chapter 3.2 --- Source-filter Model and Linear Predictive Analysis --- p.44 / Chapter 3.2.1 --- Source-filter Speech Model --- p.44 / Chapter 3.2.2 --- Linear Predictive Analysis for Speech Signal --- p.46 / Chapter 3.3 --- Vocal Tract Features --- p.51 / Chapter 3.4 --- Vocal Source Features --- p.52 / Chapter 3.4.1 --- Source Related Features: An Overview --- p.52 / Chapter 3.4.2 --- Source Related Features: Technical Viewpoints --- p.54 / Chapter 3.5 --- Effects of Noises on Speech Properties --- p.55 / Chapter 3.6 --- Summary --- p.61 / Chapter 4 --- Estimation of Robust Acoustic Features for Speaker Discrimination --- p.62 / Chapter 4.1 --- Robust Speech Techniques --- p.63 / Chapter 4.1.1 --- Noise Resilience --- p.64 / Chapter 4.1.2 --- Speech Enhancement --- p.64 / Chapter 4.2 --- Spectral Subtractive-Type Preprocessing --- p.65 / Chapter 4.2.1 --- Noise Estimation --- p.66 / Chapter 4.2.2 --- Spectral Subtraction Algorithm --- p.66 / Chapter 4.3 --- LP Analysis of Noisy Speech --- p.67 / Chapter 4.3.1 --- LP Inverse Filtering: Whitening Process --- p.68 / Chapter 4.3.2 --- Magnitude Response of All-pole Filter in Noisy Condition --- p.70 / Chapter 4.3.3 --- Noise Spectral Reshaping --- p.72 / Chapter 4.4 --- Distinctive Vocal Tract and Vocal Source Feature Extraction . . --- p.73 / Chapter 4.4.1 --- Vocal Tract Feature Extraction --- p.73 / Chapter 4.4.2 --- Source Feature Generation Procedure --- p.75 / Chapter 4.4.3 --- Subband-specific Parameterization Method --- p.79 / Chapter 4.5 --- Summary --- p.87 / Chapter 5 --- Speaker Recognition Tasks & Performance Evaluation --- p.88 / Chapter 5.1 --- Speaker Recognition Experimental Setup --- p.89 / Chapter 5.1.1 --- Task Description --- p.89 / Chapter 5.1.2 --- Baseline Experiments --- p.90 / Chapter 5.1.3 --- Identification and Verification Results --- p.91 / Chapter 5.2 --- Speaker Recognition using Source-tract Features --- p.92 / Chapter 5.2.1 --- Source Feature Selection --- p.92 / Chapter 5.2.2 --- Source-tract Feature Fusion --- p.94 / Chapter 5.2.3 --- Identification and Verification Results --- p.95 / Chapter 5.3 --- Performance Analysis --- p.98 / Chapter 6 --- Conclusion --- p.102 / Chapter 6.1 --- Discussion and Conclusion --- p.102 / Chapter 6.2 --- Suggestion of Future Work --- p.104

No description available.

No description available.

Lynn Williams’ research has focused on development of a new model of phonological intervention called multiple oppositions that has been the basis of federally funded intervention studies by the National Institutes of Health (NIH); she has authored several articles in a variety of journals, as well as published several book chapters; developed a phonological intervention software program called Sound Contrasts in Phonology (SCIP) that was funded by NIH; authored a book Speech Disorders Resource Guide for Preschool Children; and served as associate editor of Language, Speech, and Hearing Services in the Schools and the American Journal of Speech-Language Pathology. She has recently edited a book on Interventions for Speech Sound Disorders in Children that was published in 2010 by Brookes Publishing. Dr. Williams has been a frequent presenter at numerous state, national, and international conferences.

This session is developed by, and presenters invited by Speech Sound Disorders in Children. A case-based approach will be used to assess the complexity of SSD through assessment and analysis measures that guide clinical decisions regarding differential diagnosis, intervention planning, and progress monitoring.

No description available.

No description available.

No description available.