feat: 完整中文翻译 maths-cs-ai-compendium(数学·计算机科学·AI 知识大全)
翻译自英文原版 maths-cs-ai-compendium,共 20 章全部完成。 第01章 向量 | 第02章 矩阵 | 第03章 微积分 第04章 统计学 | 第05章 概率论 | 第06章 机器学习 第07章 计算语言学 | 第08章 计算机视觉 | 第09章 音频与语音 第10章 多模态学习 | 第11章 自主系统 | 第12章 图神经网络 第13章 计算与操作系统 | 第14章 数据结构与算法 第15章 生产级软件工程 | 第16章 SIMD与GPU编程 第17章 AI推理 | 第18章 ML系统设计 第19章 应用人工智能 | 第20章 前沿人工智能 翻译说明: - 所有数学公式 $...$ / $$...$$、代码块、图片引用完整保留 - mkdocs.yml 配置中文导航 + language: zh - README.md 已翻译为中文(兼 docs/index.md) - docs/ 目录包含指向各章文件的 symlink - 约 29,000 行中文内容,排除 .cache/ 构建缓存
This commit is contained in:
@@ -0,0 +1,95 @@
|
||||
<svg width="700" height="300" xmlns="http://www.w3.org/2000/svg">
|
||||
<defs>
|
||||
<marker id="mp-arrow" markerWidth="10" markerHeight="8" refX="10" refY="4" orient="auto">
|
||||
<polygon points="0,0 10,4 0,8" fill="#3498db"/>
|
||||
</marker>
|
||||
<marker id="mp-arrow-down" markerWidth="8" markerHeight="10" refX="4" refY="10" orient="auto">
|
||||
<polygon points="0,0 4,10 8,0" fill="#3498db"/>
|
||||
</marker>
|
||||
</defs>
|
||||
|
||||
<text x="350" y="22" fill="#333" font-size="14" font-weight="bold" text-anchor="middle">MFCC Feature Extraction Pipeline</text>
|
||||
|
||||
<!-- ===== Row 1: Signal -> Pre-emphasis -> Framing/Windowing -> FFT ===== -->
|
||||
|
||||
<!-- Box 1: Signal -->
|
||||
<rect x="20" y="50" width="80" height="38" rx="6" fill="#3498db" fill-opacity="0.1" stroke="#3498db" stroke-width="1.5"/>
|
||||
<text x="60" y="73" fill="#3498db" font-size="10" font-weight="bold" text-anchor="middle">Signal</text>
|
||||
<text x="60" y="102" fill="#666" font-size="8" text-anchor="middle">Raw audio x[n]</text>
|
||||
|
||||
<!-- Arrow 1->2 -->
|
||||
<line x1="100" y1="69" x2="130" y2="69" stroke="#3498db" stroke-width="1.5" marker-end="url(#mp-arrow)"/>
|
||||
|
||||
<!-- Box 2: Pre-emphasis -->
|
||||
<rect x="140" y="50" width="95" height="38" rx="6" fill="#e74c3c" fill-opacity="0.1" stroke="#e74c3c" stroke-width="1.5"/>
|
||||
<text x="187" y="66" fill="#e74c3c" font-size="9" font-weight="bold" text-anchor="middle">Pre-</text>
|
||||
<text x="187" y="78" fill="#e74c3c" font-size="9" font-weight="bold" text-anchor="middle">emphasis</text>
|
||||
<text x="187" y="102" fill="#666" font-size="8" text-anchor="middle">y[n]=x[n]-ax[n-1]</text>
|
||||
|
||||
<!-- Arrow 2->3 -->
|
||||
<line x1="235" y1="69" x2="265" y2="69" stroke="#3498db" stroke-width="1.5" marker-end="url(#mp-arrow)"/>
|
||||
|
||||
<!-- Box 3: Framing + Windowing -->
|
||||
<rect x="275" y="50" width="95" height="38" rx="6" fill="#27ae60" fill-opacity="0.1" stroke="#27ae60" stroke-width="1.5"/>
|
||||
<text x="322" y="66" fill="#27ae60" font-size="9" font-weight="bold" text-anchor="middle">Framing +</text>
|
||||
<text x="322" y="78" fill="#27ae60" font-size="9" font-weight="bold" text-anchor="middle">Windowing</text>
|
||||
<text x="322" y="102" fill="#666" font-size="8" text-anchor="middle">20-40ms Hamming</text>
|
||||
|
||||
<!-- Arrow 3->4 -->
|
||||
<line x1="370" y1="69" x2="400" y2="69" stroke="#3498db" stroke-width="1.5" marker-end="url(#mp-arrow)"/>
|
||||
|
||||
<!-- Box 4: FFT -->
|
||||
<rect x="410" y="50" width="80" height="38" rx="6" fill="#f39c12" fill-opacity="0.1" stroke="#f39c12" stroke-width="1.5"/>
|
||||
<text x="450" y="73" fill="#f39c12" font-size="10" font-weight="bold" text-anchor="middle">FFT</text>
|
||||
<text x="450" y="102" fill="#666" font-size="8" text-anchor="middle">Power spectrum</text>
|
||||
|
||||
<!-- Turn arrow: from FFT down and back to row 2 -->
|
||||
<path d="M 490,69 L 530,69 L 530,155 L 80,155 L 80,170" fill="none" stroke="#3498db" stroke-width="1.5" marker-end="url(#mp-arrow-down)"/>
|
||||
<text x="305" y="148" fill="#3498db" font-size="8" text-anchor="middle" font-style="italic">apply to each frame</text>
|
||||
|
||||
<!-- ===== Row 2: Mel Filterbank -> Log -> DCT -> MFCCs ===== -->
|
||||
|
||||
<!-- Box 5: Mel Filterbank -->
|
||||
<rect x="30" y="180" width="100" height="38" rx="6" fill="#9b59b6" fill-opacity="0.1" stroke="#9b59b6" stroke-width="1.5"/>
|
||||
<text x="80" y="196" fill="#9b59b6" font-size="9" font-weight="bold" text-anchor="middle">Mel</text>
|
||||
<text x="80" y="208" fill="#9b59b6" font-size="9" font-weight="bold" text-anchor="middle">Filterbank</text>
|
||||
<text x="80" y="232" fill="#666" font-size="8" text-anchor="middle">Triangular filters</text>
|
||||
|
||||
<!-- Arrow 5->6 -->
|
||||
<line x1="130" y1="199" x2="160" y2="199" stroke="#3498db" stroke-width="1.5" marker-end="url(#mp-arrow)"/>
|
||||
|
||||
<!-- Box 6: Log -->
|
||||
<rect x="170" y="180" width="70" height="38" rx="6" fill="#e74c3c" fill-opacity="0.1" stroke="#e74c3c" stroke-width="1.5"/>
|
||||
<text x="205" y="203" fill="#e74c3c" font-size="10" font-weight="bold" text-anchor="middle">Log</text>
|
||||
<text x="205" y="232" fill="#666" font-size="8" text-anchor="middle">Compress range</text>
|
||||
|
||||
<!-- Arrow 6->7 -->
|
||||
<line x1="240" y1="199" x2="270" y2="199" stroke="#3498db" stroke-width="1.5" marker-end="url(#mp-arrow)"/>
|
||||
|
||||
<!-- Box 7: DCT -->
|
||||
<rect x="280" y="180" width="70" height="38" rx="6" fill="#27ae60" fill-opacity="0.1" stroke="#27ae60" stroke-width="1.5"/>
|
||||
<text x="315" y="203" fill="#27ae60" font-size="10" font-weight="bold" text-anchor="middle">DCT</text>
|
||||
<text x="315" y="232" fill="#666" font-size="8" text-anchor="middle">Decorrelate</text>
|
||||
|
||||
<!-- Arrow 7->8 -->
|
||||
<line x1="350" y1="199" x2="385" y2="199" stroke="#3498db" stroke-width="1.5" marker-end="url(#mp-arrow)"/>
|
||||
|
||||
<!-- Box 8: MFCCs (output, highlighted) -->
|
||||
<rect x="395" y="174" width="115" height="50" rx="8" fill="#3498db" fill-opacity="0.15" stroke="#3498db" stroke-width="2"/>
|
||||
<text x="452" y="197" fill="#3498db" font-size="12" font-weight="bold" text-anchor="middle">MFCCs</text>
|
||||
<text x="452" y="213" fill="#3498db" font-size="9" text-anchor="middle">12-13 coefficients</text>
|
||||
|
||||
<!-- Dashed arrow to Deltas box -->
|
||||
<line x1="510" y1="199" x2="535" y2="199" stroke="#999" stroke-width="1.2" stroke-dasharray="4,3" marker-end="url(#mp-arrow)"/>
|
||||
|
||||
<!-- Optional Deltas box -->
|
||||
<rect x="545" y="174" width="130" height="50" rx="6" fill="#f5f5f5" stroke="#ddd" stroke-width="1"/>
|
||||
<text x="610" y="192" fill="#333" font-size="9" font-weight="bold" text-anchor="middle">+ Delta Features</text>
|
||||
<text x="610" y="205" fill="#666" font-size="8" text-anchor="middle">1st derivative (velocity)</text>
|
||||
<text x="610" y="217" fill="#666" font-size="8" text-anchor="middle">2nd derivative (accel.)</text>
|
||||
|
||||
<!-- Bottom note -->
|
||||
<rect x="60" y="255" width="580" height="36" rx="4" fill="#f5f5f5" stroke="#333" stroke-width="0.8"/>
|
||||
<text x="350" y="270" fill="#333" font-size="10" text-anchor="middle">MFCCs: compact representation of spectral shape, standard features for speech</text>
|
||||
<text x="350" y="284" fill="#666" font-size="9" text-anchor="middle">Typical setup: 13 MFCCs + 13 deltas + 13 delta-deltas = 39 features per frame</text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 5.9 KiB |
Reference in New Issue
Block a user