還研究了相位延遲域和群延遲域中的加性噪聲和信道失真影響，並將結果用于推導gVTS方程。HMM/GMM中的Aurora-4 ASR任務和基于DNN的瓶頸系統在clean和多樣式訓練模式下的實驗結果證實了該方法在處理加性噪聲和信道噪聲方面的有效性。 The Fourier analysis plays a key role in speech signal processing. As a complex quantity錛 it can be expressed in the polar form using the magnitude and phase spectra. The magnitude spectrum is widely used in almost every corner of speech processing. However錛 the phase spectrum is not an obviously appealing start point for processing the speech signal. In contrast to the magnitude spectrum whose fine and coarse structures have a clear relation to speech perception錛 the phase spectrum is difficult to interpret and manipulate. In fact錛 there is not a meaningful trend or extrema which may facilitate the modelling process. Nonetheless錛 the speech phase spectrum has recently gained renewed attention. An expanding body of work is showing that it can be usefully employed in a multitude of speech processing applications.Now that the potential for the phase-based speech processing has been established錛 there is a need for a fundamental model to help understand the way in which phase encodes speech information.In this thesis a novel phase-domain source-flter model is proposed that allows for deconvolution of the speech vocal tract (flter) and excitation (source) components through phase processing. This model utilises the Hilbert transform錛 shows how the excitation and vocal tract elements mix in the phase domain and provides a framework for efficiently segregating the source and filter components through phase manipulation. To investigate the efficacy of the suggested approach錛 a set of features is extracted from the phase filter part for automatic speech recognition (ASR) and the source part of the phase is utilised for fundamental frequency estimation. Accuracy and robustness in both cases are illustrated and discussed. In addition錛 the proposed approach is improved by replacing the log with the generalised logarithmic function in the Hilbert transform and also by computing the group delay via regression filter.Furthermore錛 statistical distribution of the phase spectrum and its representations along the feature extraction pipeline are studied. It is illustrated that the phase spectrum has a bell-shaped distribution. Some statistical normalisation methods such as mean-variance normalisation錛 Laplacianisation錛 Gaussianisation and Histogram equalisation are successfully applied to the phase-based features and lead to a significant robustness improvement.The robustness gain achieved through using statistical normalisation and generalized logarithmic function encouraged the use of more advanced model-based statistical techniques such as vector Taylor Series (VTS). VTS in its original formulation assumes usage of the log function for compression. In order to simultaneously take advantage of the VTS and generalised logarithmic function錛 a new formulation is first developed to merge both into a unified framework called generalised VTS (gVTS). Also in order to leverage the gVTS framework錛 a novel channel noise estimation method is developed. The extensions of the gVTS framework and the proposed channel estimation to the group delay domain are then explored. The problems it presents are analysed and discussed錛 some solutions are proposed and fnally the corresponding formulae are derived. Moreover錛 the effect of additive noise and channel distortion in the phase and group delay domains are scrutinised and the results are utilised in deriving the gVTS equations. Experimental results in the Aurora-4 ASR task in an HMM/GMM set up along with a DNN-based bottleneck system in the clean and multi-style training modes confirmed the efficacy of the proposed approach in dealing with both additive and channel noise. 1. 引言2. 背景與相關工作3. 相位信息4. 相位域的源-濾波器分離5. 用于魯棒ASR的相位/群時延域的廣義VTS6. 結論與未來工作展望附錄A 希爾伯特變換附錄B 用于魯棒ASR的廣義向量泰勒級數（gVTS）方法附錄C 基于廣義向量泰勒級數的信道噪聲估計附錄D 用于ASR的深度神經網絡附錄E 使用的數據庫描述附錄F 特征提取技術回顧更多精彩文章請關注公眾號：厄爾尼諾指數進入上升區間： 2020年2月11日晚報 楊學祥，楊冬紅關鍵提示： 潮汐組合類型轉換具有13.6天週期，即雙週循環，這在圖1-2中都有明顯的表現。除此之外，兩週之內厄爾尼諾指數往往出現兩個峰值和兩個谷值，即次一級的7天週期。這一週期在氣溫變化中也有明顯的表現（見圖）。 潮汐不僅有13.6天週期，而且存在7.1天和9.1天週期。1921年杜德生對月亮和太陽引潮力位進行了嚴格的調和級數展開，在展開中約有90項長週期成分。其中振幅超過這90項長週期振幅之和的0.5%的共有20個，在這20個中就有9天項和7天項（見圖1）。圖1 2020年2月10日18時厄爾尼諾指數為+0.257，比2月10日12時厄爾尼諾指數+0.260， 減速0.003，減速變慢，進入下降區間。圖2 2020年2月11日00時厄爾尼諾指數為+0.259，比2月10日18時厄爾尼諾指數+0.257， 增速0.002，
