“TTS-project-synthesis”版本间的差异
来自cslt Wiki
| 第12行： | 第12行： | ||
==<font color="red">Mono-speaker TTS</font>== | ==<font color="red">Mono-speaker TTS</font>== | ||
| − | *Female | + | *Female[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/huilian/female01/female01_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/huilian/female01/female01_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
| − | *Male | + | *Male[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/huilian/male01/male01_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/huilian/male01/male01_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
| − | *Child | + | *Child[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/huilian/child01.neutral/child01-neutral_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/huilian/child01.neutral/child01-neutral_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
<h1> <font color="red">Mix-training without speaker-vector</font></h1> | <h1> <font color="red">Mix-training without speaker-vector</font></h1> | ||
| − | *Female & Male | + | *Female & Male[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/female01-male01/female01-male01_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/female01-male01/female01-male01_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
| − | *Female * Child | + | *Female * Child[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/female01-child01.neutral/female01-child.neutral_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/female01-child01.neutral/female01-child.neutral_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
| − | *Male & Child | + | *Male & Child[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/male01-child01.neutral/male01_child01.neutral_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/male01-child01.neutral/male01_child01.neutral_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
==<font color="red">Multi-speaker TTS</font>== | ==<font color="red">Multi-speaker TTS</font>== | ||
*Single person=== | *Single person=== | ||
| − | :*Female | + | :*Female[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/all.dvector40/female01.dvec40_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/all.dvector40/female01.dvec40_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
| − | :*Male | + | :*Male[http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/all.dvector40/male01.dvec40_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] |
| − | [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/multi-speakers/mix/all.dvector40/male01.dvec40_5_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav] | + | |
*Interpolation | *Interpolation | ||
:* Female & Male with different ratio | :* Female & Male with different ratio | ||
2017年12月1日 (五) 02:21的版本
目录
Project name
Text To Speech
Project members
Dong Wang, Zhiyong Zhang
Introduction
xxx
Sample waves
Synthesis text:好雨知时节，当春乃发声，随风潜入夜，润物细无声
Mono-speaker TTS
- Female[1]
- Male[2]
- Child[3]
Mix-training without speaker-vector
- Female & Male[4]
- Female * Child[5]
- Male & Child[6]
Multi-speaker TTS
- Single person===
- Female[7]
- Male[8]
- Interpolation
- Female & Male with different ratio
