現(xiàn)代語音處理技術(shù)及應(yīng)用

第1章 緒論                  
                   
 1.1 概述                  
 1.2 語音處理的研究方法                  
 1.3 語音處理的應(yīng)用                  
 1.4 本書的內(nèi)容與組織                  
 1.5 習題                  
                   
 第2章 語音信號處理基礎(chǔ)                  
                   
 2.1 語音的波形及特性                   
 2.2 語音的產(chǎn)生                  
 2.3 漢語語音的基本特性                  
 2.4 語音信號的簡化數(shù)字模型                  
 2.5 聽覺系統(tǒng)和聽覺特性                  
 2.6 小結(jié)                  
 2.7 習題                  
                   
 第3章 語音信號的時域分析                  
                   
 3.1 概述                   
 3.2 語音短時分析技術(shù)                  
 3.3 短時能量和平均幅度                  
 3.4 短時平均過零率                  
 3.5 短時自相關(guān)分析                  
 3.6 語音端點檢測                  
 3.7 基音周期估計                  
 3.8 小結(jié)                  
 3.9 習題                  
                   
 第4章 語音信號的變換分析                  
                   
 4.1 語音信號的頻域分析                   
 4.2 語音信號的同態(tài)處理                  
 4.3 語音信號的非線性處理                  
 4.4 分形內(nèi)插語音編碼算法                  
 4.5 小結(jié)                  
 4.6 習題                  
                   
 第5章 語音信號線性預測分析                  
                   
 5.1 LP分析的基本原理                   
 5.2 LP正則方程的自相關(guān)解法和自協(xié)方差解法                  
 5.3 模型增益G的確定                  
 5.4 線譜對LSP分析                  
 5.5 LP導出的其他語音參數(shù)                  
 5.6 LP分析的頻域解釋                  
 5.7 小結(jié)                  
 5.8 習題                  
                   
 第6章 矢量量化                  
                   
 6.1 概述                   
 6.2 無記憶矢量量化器                  
 6.3 有記憶矢量量化器                  
 6.4 特片矢量及失真測度                  
 6.5 小結(jié)                  
 6.6 習題                  
                   
 第7章 語音編碼                  
                   
 7.1 語音編碼的基本概念                   
 7.2 波形編碼                  
 7.3 參數(shù)編碼和混合編碼                  
 7.4 混合激勵線性預測MELP                  
 7.5 語音編碼的質(zhì)量評估                  
 7.6 小結(jié)                  
 7.7 習題                  
                   
 第8章 語音識別                  
                   
 8.1 概述                   
 8.2 動態(tài)時間規(guī)整                  
 8.3 隱馬爾可夫模型                  
 8.4 HMM的基本問題                  
 8.5 連續(xù)HMM和半連續(xù)HMM                  
 8.6 HMM相似度的比較                  
 8.7 HMM的應(yīng)用                  
 8.8 孤立詞識別                  
 8.9 連接詞識別                  
 8.10 連續(xù)語音識別                  
 8.11 說話人自適應(yīng)技術(shù)                  
 8.12 關(guān)鍵詞確認                  
 8.13 說話人識別                  
 8.14 人工神經(jīng)網(wǎng)絡(luò)在語音識別中的應(yīng)用                  
 8.15 魯校語音識別的研究                  
 8.16 小結(jié)                  
 8.17 習題                  
                   
 第9章 語音合成                  
                   
 9.1 概述                   
 9.2 文-語轉(zhuǎn)換系統(tǒng)                  
 9.3 文本分析                  
 9.4 韻律生成                  
 9.5 語音生成                  
 9.6 小結(jié)                  
 9.7 習題                  
                   
 第10章 語音增強                  
                   
 10.1 概述                   
 10.2 基于語音譜特征的諧波增強算法                  
 10.3 基于短時譜估計的增強算法                  
 10.4 基于信號子空間的增強算法                  
 10.5 基于語音生成模型的增強算法                  
 10.6 語音增強的新發(fā)展                  
 10.7 小結(jié)                  
 10.8 習題                  
                   
 第11章 語音通信應(yīng)用中的關(guān)鍵技術(shù)                  
                   
 11.1 不連續(xù)傳輸DTX                   
 11.2 語音激活檢測VAD                  
 11.3 回波抵消                  
 11.4 聲碼器同步                  
 11.5 糾錯編碼                  
 11.6 小結(jié)                  
 11.7 習題                  
                   
 第12章 語音處理的實時實現(xiàn)                  
                   
 12.1 DSP語音處理系統(tǒng)                   
 12.2 可編程DSP芯片應(yīng)用基礎(chǔ)                  
 12.3 CCS DSP集成開發(fā)環(huán)境                  
 12.4 一個基于TMS320VC5409 DSP應(yīng)用系統(tǒng)的開發(fā)                  
 12.5 小結(jié)                  
 12.6 習題                  
                   
 附錄