htk 工具使用介绍
来源:互联网 发布:安卓软件开发编程论坛 编辑:程序博客网 时间:2024/05/19 22:07
tool example:
./HList -h -s 2000 -e 3000 -F WAV ./data/train/speech/s100.wav
------------------- Source: ./data/train/speech/s100.wav --------------------
Sample Bytes: 2 Sample Kind: WAVEFORM
Num Comps: 1 Sample Period: 125.0 us
Num Samples: 27649 File Format: WAV
--------------------------- Samples: 10000->10050 ---------------------------
10000: -397 -19 622 1420 865 -970 -1819 -1765 -2084 -2440
10010: -2825 -3014 -2899 -2545 -1752 -1426 -1659 -2261 -2961 -2974
10020: -2423 -1814 -1408 -478 499 1299 3111 3874 2624 1534
10030: 1752 2584 2457 2652 3304 3004 2536 1853 927 342
10040: 872 2284 2628 1508 -410 -2086 -1769 -103 890 979
10050: 1179
------------------------------------ END ------------------------------------
config_hlist内容如下
# Coding parameters wav-->mfcc
SOURCEFORMAT = WAV
#SOURCEFORMAT = HTK
TARGETKIND = MFCC_0_D_A
TARGETRATE = 100000.0 #10ms frame rate
#SAVECOMPRESSED = T
#SAVEWITHCRC = T
WINDOWSIZE = 250000.0 #25ms window
USEHAMMING = T
PREEMCOEF = 0.97
NUMCHANS = 26
CEPLIFTER = 22
NUMCEPS = 12
ENORMALISE = F
HList:
The second use of HList is to check that input conversions are being performed properly.
./HList -C config_hlist -o -h -t -s 100 -e 104 -i 9 ./data/train/speech/s100.wav
--------------------- Source: ./data/train/speech/s100.wav ---------------------
Sample Bytes: 2 Sample Kind: WAVEFORM
Num Comps: 1 Sample Period: 125.0 us
Num Samples: 27649 File Format: WAV
------------------------------------ Target ------------------------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
---------------------------- Observation Structure -----------------------------
x: MFCC-1 MFCC-2 MFCC-3 MFCC-4 MFCC-5 MFCC-6 MFCC-7 MFCC-8 MFCC-9
MFCC-10 MFCC-11 MFCC-12 C0 Del-1 Del-2 Del-3 Del-4 Del-5
Del-6 Del-7 Del-8 Del-9 Del-10 Del-11 Del-12 DelC0 Acc-1
Acc-2 Acc-3 Acc-4 Acc-5 Acc-6 Acc-7 Acc-8 Acc-9 Acc-10
Acc-11 Acc-12 AccC0
------------------------------ Samples: 100->104 -------------------------------
100: -7.180 -22.617 -6.168 2.428 -0.199 -17.704 -2.686 -14.413 -0.158
-6.712 9.965 -11.494 82.375 -0.119 0.314 -0.004 -0.138 -0.223
-0.441 0.518 0.228 1.403 0.142 0.050 -0.286 0.102 0.009
0.110 0.110 0.327 0.111 -0.264 -0.196 0.152 0.351 -0.119
0.020 -0.125 -0.058
101: -7.572 -22.348 -5.803 3.392 -0.744 -18.759 -3.146 -13.781 2.432
-8.324 10.059 -12.708 82.342 -0.096 0.365 0.402 0.237 0.622
-0.686 0.655 -0.134 1.722 0.108 0.366 -0.321 -0.008 0.024
0.015 0.111 0.165 0.434 -0.077 -0.032 -0.250 -0.043 -0.070
0.335 -0.008 -0.068
102: -7.744 -21.719 -5.248 4.129 0.944 -18.975 -2.915 -12.113 4.839
-6.693 11.414 -11.875 82.368 -0.186 0.187 0.202 0.096 0.870
-0.748 0.169 -0.929 0.656 -0.106 0.547 -0.535 -0.119 0.059
-0.113 0.001 -0.045 0.301 -0.039 0.015 -0.507 -0.373 -0.242
0.350 -0.076 -0.093
103: -7.882 -21.672 -5.241 3.332 2.088 -20.884 -2.197 -16.317 3.517
-6.993 10.256 -13.252 82.080 -0.046 -0.010 0.210 -0.218 1.186
-0.545 0.521 -1.628 0.224 -0.257 1.170 -0.423 -0.184 0.105
-0.120 -0.139 -0.074 -0.014 -0.046 0.006 -0.168 -0.210 -0.374
0.248 -0.111 -0.096
104: -7.953 -22.022 -5.440 2.941 2.737 -20.379 -2.314 -17.791 2.579
-7.909 12.600 -13.895 81.909 0.152 -0.065 0.096 -0.136 0.998
-0.707 0.661 -1.558 0.288 -0.886 1.398 -0.614 -0.274 0.088
-0.024 -0.260 -0.025 -0.287 -0.118 -0.134 0.292 -0.058 -0.369
-0.170 -0.053 -0.096
------------------------------------- END --------------------------------------
./HList -n 3 (3 streams)
./HList -C config_hlist -n 3 -o -h -t -s 100 -e 101 -i 9 ./data/train/speech/s100.wav
--------------------- Source: ./data/train/speech/s100.wav ---------------------
Sample Bytes: 2 Sample Kind: WAVEFORM
Num Comps: 1 Sample Period: 125.0 us
Num Samples: 27649 File Format: WAV
------------------------------------ Target ------------------------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
---------------------------- Observation Structure -----------------------------
x.1: MFCC-1 MFCC-2 MFCC-3 MFCC-4 MFCC-5 MFCC-6 MFCC-7 MFCC-8 MFCC-9
MFCC-10 MFCC-11 MFCC-12 C0
x.2: Del-1 Del-2 Del-3 Del-4 Del-5 Del-6 Del-7 Del-8 Del-9
Del-10 Del-11 Del-12 DelC0
x.3: Acc-1 Acc-2 Acc-3 Acc-4 Acc-5 Acc-6 Acc-7 Acc-8 Acc-9
Acc-10 Acc-11 Acc-12 AccC0
------------------------------ Samples: 100->101 -------------------------------
100.1: -7.180 -22.617 -6.168 2.428 -0.199 -17.704 -2.686 -14.413 -0.158
-6.712 9.965 -11.494 82.375
100.2: -0.119 0.314 -0.004 -0.138 -0.223 -0.441 0.518 0.228 1.403
0.142 0.050 -0.286 0.102
100.3: 0.009 0.110 0.110 0.327 0.111 -0.264 -0.196 0.152 0.351
-0.119 0.020 -0.125 -0.058
101.1: -7.572 -22.348 -5.803 3.392 -0.744 -18.759 -3.146 -13.781 2.432
-8.324 10.059 -12.708 82.342
101.2: -0.096 0.365 0.402 0.237 0.622 -0.686 0.655 -0.134 1.722
0.108 0.366 -0.321 -0.008
101.3: 0.024 0.015 0.111 0.165 0.434 -0.077 -0.032 -0.250 -0.043
-0.070 0.335 -0.008 -0.068
------------------------------------- END --------------------------------------
./HList -o -h -t -s 100 -e 101 -i 9 ./data/train/feature/s100.mfc
-------------------- Source: ./data/train/feature/s100.mfc ---------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_K_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
------------------------------------ Target ------------------------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
---------------------------- Observation Structure -----------------------------
x: MFCC-1 MFCC-2 MFCC-3 MFCC-4 MFCC-5 MFCC-6 MFCC-7 MFCC-8 MFCC-9
MFCC-10 MFCC-11 MFCC-12 C0 Del-1 Del-2 Del-3 Del-4 Del-5
Del-6 Del-7 Del-8 Del-9 Del-10 Del-11 Del-12 DelC0 Acc-1
Acc-2 Acc-3 Acc-4 Acc-5 Acc-6 Acc-7 Acc-8 Acc-9 Acc-10
Acc-11 Acc-12 AccC0
------------------------------ Samples: 100->101 -------------------------------
100: -7.180 -22.617 -6.168 2.428 -0.199 -17.704 -2.686 -14.413 -0.158
-6.712 9.965 -11.494 82.375 -0.119 0.314 -0.004 -0.138 -0.223
-0.441 0.518 0.228 1.403 0.142 0.050 -0.286 0.102 0.009
0.110 0.110 0.327 0.111 -0.264 -0.196 0.152 0.351 -0.119
0.020 -0.125 -0.058
101: -7.572 -22.348 -5.803 3.392 -0.744 -18.759 -3.146 -13.781 2.432
-8.324 10.059 -12.708 82.342 -0.096 0.365 0.402 0.237 0.622
-0.686 0.655 -0.134 1.722 0.108 0.366 -0.321 -0.008 0.024
0.015 0.111 0.165 0.434 -0.077 -0.032 -0.250 -0.043 -0.070
0.335 -0.008 -0.068
------------------------------------- END --------------------------------------
./HList -h -s 2000 -e 3000 -F WAV ./data/train/speech/s100.wav
------------------- Source: ./data/train/speech/s100.wav --------------------
Sample Bytes: 2 Sample Kind: WAVEFORM
Num Comps: 1 Sample Period: 125.0 us
Num Samples: 27649 File Format: WAV
--------------------------- Samples: 10000->10050 ---------------------------
10000: -397 -19 622 1420 865 -970 -1819 -1765 -2084 -2440
10010: -2825 -3014 -2899 -2545 -1752 -1426 -1659 -2261 -2961 -2974
10020: -2423 -1814 -1408 -478 499 1299 3111 3874 2624 1534
10030: 1752 2584 2457 2652 3304 3004 2536 1853 927 342
10040: 872 2284 2628 1508 -410 -2086 -1769 -103 890 979
10050: 1179
------------------------------------ END ------------------------------------
config_hlist内容如下
# Coding parameters wav-->mfcc
SOURCEFORMAT = WAV
#SOURCEFORMAT = HTK
TARGETKIND = MFCC_0_D_A
TARGETRATE = 100000.0 #10ms frame rate
#SAVECOMPRESSED = T
#SAVEWITHCRC = T
WINDOWSIZE = 250000.0 #25ms window
USEHAMMING = T
PREEMCOEF = 0.97
NUMCHANS = 26
CEPLIFTER = 22
NUMCEPS = 12
ENORMALISE = F
HList:
The second use of HList is to check that input conversions are being performed properly.
./HList -C config_hlist -o -h -t -s 100 -e 104 -i 9 ./data/train/speech/s100.wav
--------------------- Source: ./data/train/speech/s100.wav ---------------------
Sample Bytes: 2 Sample Kind: WAVEFORM
Num Comps: 1 Sample Period: 125.0 us
Num Samples: 27649 File Format: WAV
------------------------------------ Target ------------------------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
---------------------------- Observation Structure -----------------------------
x: MFCC-1 MFCC-2 MFCC-3 MFCC-4 MFCC-5 MFCC-6 MFCC-7 MFCC-8 MFCC-9
MFCC-10 MFCC-11 MFCC-12 C0 Del-1 Del-2 Del-3 Del-4 Del-5
Del-6 Del-7 Del-8 Del-9 Del-10 Del-11 Del-12 DelC0 Acc-1
Acc-2 Acc-3 Acc-4 Acc-5 Acc-6 Acc-7 Acc-8 Acc-9 Acc-10
Acc-11 Acc-12 AccC0
------------------------------ Samples: 100->104 -------------------------------
100: -7.180 -22.617 -6.168 2.428 -0.199 -17.704 -2.686 -14.413 -0.158
-6.712 9.965 -11.494 82.375 -0.119 0.314 -0.004 -0.138 -0.223
-0.441 0.518 0.228 1.403 0.142 0.050 -0.286 0.102 0.009
0.110 0.110 0.327 0.111 -0.264 -0.196 0.152 0.351 -0.119
0.020 -0.125 -0.058
101: -7.572 -22.348 -5.803 3.392 -0.744 -18.759 -3.146 -13.781 2.432
-8.324 10.059 -12.708 82.342 -0.096 0.365 0.402 0.237 0.622
-0.686 0.655 -0.134 1.722 0.108 0.366 -0.321 -0.008 0.024
0.015 0.111 0.165 0.434 -0.077 -0.032 -0.250 -0.043 -0.070
0.335 -0.008 -0.068
102: -7.744 -21.719 -5.248 4.129 0.944 -18.975 -2.915 -12.113 4.839
-6.693 11.414 -11.875 82.368 -0.186 0.187 0.202 0.096 0.870
-0.748 0.169 -0.929 0.656 -0.106 0.547 -0.535 -0.119 0.059
-0.113 0.001 -0.045 0.301 -0.039 0.015 -0.507 -0.373 -0.242
0.350 -0.076 -0.093
103: -7.882 -21.672 -5.241 3.332 2.088 -20.884 -2.197 -16.317 3.517
-6.993 10.256 -13.252 82.080 -0.046 -0.010 0.210 -0.218 1.186
-0.545 0.521 -1.628 0.224 -0.257 1.170 -0.423 -0.184 0.105
-0.120 -0.139 -0.074 -0.014 -0.046 0.006 -0.168 -0.210 -0.374
0.248 -0.111 -0.096
104: -7.953 -22.022 -5.440 2.941 2.737 -20.379 -2.314 -17.791 2.579
-7.909 12.600 -13.895 81.909 0.152 -0.065 0.096 -0.136 0.998
-0.707 0.661 -1.558 0.288 -0.886 1.398 -0.614 -0.274 0.088
-0.024 -0.260 -0.025 -0.287 -0.118 -0.134 0.292 -0.058 -0.369
-0.170 -0.053 -0.096
------------------------------------- END --------------------------------------
./HList -n 3 (3 streams)
./HList -C config_hlist -n 3 -o -h -t -s 100 -e 101 -i 9 ./data/train/speech/s100.wav
--------------------- Source: ./data/train/speech/s100.wav ---------------------
Sample Bytes: 2 Sample Kind: WAVEFORM
Num Comps: 1 Sample Period: 125.0 us
Num Samples: 27649 File Format: WAV
------------------------------------ Target ------------------------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
---------------------------- Observation Structure -----------------------------
x.1: MFCC-1 MFCC-2 MFCC-3 MFCC-4 MFCC-5 MFCC-6 MFCC-7 MFCC-8 MFCC-9
MFCC-10 MFCC-11 MFCC-12 C0
x.2: Del-1 Del-2 Del-3 Del-4 Del-5 Del-6 Del-7 Del-8 Del-9
Del-10 Del-11 Del-12 DelC0
x.3: Acc-1 Acc-2 Acc-3 Acc-4 Acc-5 Acc-6 Acc-7 Acc-8 Acc-9
Acc-10 Acc-11 Acc-12 AccC0
------------------------------ Samples: 100->101 -------------------------------
100.1: -7.180 -22.617 -6.168 2.428 -0.199 -17.704 -2.686 -14.413 -0.158
-6.712 9.965 -11.494 82.375
100.2: -0.119 0.314 -0.004 -0.138 -0.223 -0.441 0.518 0.228 1.403
0.142 0.050 -0.286 0.102
100.3: 0.009 0.110 0.110 0.327 0.111 -0.264 -0.196 0.152 0.351
-0.119 0.020 -0.125 -0.058
101.1: -7.572 -22.348 -5.803 3.392 -0.744 -18.759 -3.146 -13.781 2.432
-8.324 10.059 -12.708 82.342
101.2: -0.096 0.365 0.402 0.237 0.622 -0.686 0.655 -0.134 1.722
0.108 0.366 -0.321 -0.008
101.3: 0.024 0.015 0.111 0.165 0.434 -0.077 -0.032 -0.250 -0.043
-0.070 0.335 -0.008 -0.068
------------------------------------- END --------------------------------------
./HList -o -h -t -s 100 -e 101 -i 9 ./data/train/feature/s100.mfc
-------------------- Source: ./data/train/feature/s100.mfc ---------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_K_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
------------------------------------ Target ------------------------------------
Sample Bytes: 156 Sample Kind: MFCC_D_A_0
Num Comps: 39 Sample Period: 10000.0 us
Num Samples: 344 File Format: HTK
---------------------------- Observation Structure -----------------------------
x: MFCC-1 MFCC-2 MFCC-3 MFCC-4 MFCC-5 MFCC-6 MFCC-7 MFCC-8 MFCC-9
MFCC-10 MFCC-11 MFCC-12 C0 Del-1 Del-2 Del-3 Del-4 Del-5
Del-6 Del-7 Del-8 Del-9 Del-10 Del-11 Del-12 DelC0 Acc-1
Acc-2 Acc-3 Acc-4 Acc-5 Acc-6 Acc-7 Acc-8 Acc-9 Acc-10
Acc-11 Acc-12 AccC0
------------------------------ Samples: 100->101 -------------------------------
100: -7.180 -22.617 -6.168 2.428 -0.199 -17.704 -2.686 -14.413 -0.158
-6.712 9.965 -11.494 82.375 -0.119 0.314 -0.004 -0.138 -0.223
-0.441 0.518 0.228 1.403 0.142 0.050 -0.286 0.102 0.009
0.110 0.110 0.327 0.111 -0.264 -0.196 0.152 0.351 -0.119
0.020 -0.125 -0.058
101: -7.572 -22.348 -5.803 3.392 -0.744 -18.759 -3.146 -13.781 2.432
-8.324 10.059 -12.708 82.342 -0.096 0.365 0.402 0.237 0.622
-0.686 0.655 -0.134 1.722 0.108 0.366 -0.321 -0.008 0.024
0.015 0.111 0.165 0.434 -0.077 -0.032 -0.250 -0.043 -0.070
0.335 -0.008 -0.068
------------------------------------- END --------------------------------------
阅读全文
0 0
- htk 工具使用介绍
- 区分性训练训练流程简述(使用HTK工具)
- HTK工具的安装
- HTK数据准备工具-HLEd
- HTK数据准备工具-HLStats
- HTK数据准备工具-HCopy
- HTK数据准备工具-HList
- HTK数据准备工具-HCopy
- HTK
- HTK
- HTK
- htk
- Ubuntu下HTK工具安装过程
- htk - lattice画图工具(plot lattice)
- HTK工具HVite代码分析1
- LaTeX 工具使用介绍
- gprof工具使用介绍
- errorstack 工具使用介绍
- jqueryUI互动效果之selectable
- [bigdata-124] docker+django2.0 构建web服务
- LC射频滤波器调试经验
- mvninstall项目报 编码GBK的不可映射字符
- nginx upload模块+python 后端处理模仿fastdfs实现文件存取
- htk 工具使用介绍
- thrift服务化改造原理分析
- Unity序列化
- 解决pcb搭线问题的过程
- 迭代对象、迭代器、生成器浅析
- Ubuntu下安装Eclipse开发环境(Eclipse IDE for C/C++ Developers)
- eclipse开发go语言入门案例
- mongodb笔记05(MongoDB 复制(副本集))
- Ubuntu 14下apache2开启对.htaccess支持