TTS-project-synthesis

来自cslt Wiki
2017年12月1日 (五) 02:01Zhangzy讨论 | 贡献的版本

跳转至: 导航搜索

Project name

Text To Speech

Project members

Dong Wang, Zhiyong Zhang

Introduction

xxx

Sample waves

Singal-training

  • Female

<a name = "Wav5">好雨知时节,当春乃发声,随风潜入夜,润物细无声</a>
<audio src='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' controls="controls"></audio> [1]

  • Male

<a name = "Wav5">好雨知时节,当春乃发声,随风潜入夜,润物细无声</a>
<audio src='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' controls="controls"></audio>

  • Child

<a name = "Wav5">好雨知时节,当春乃发声,随风潜入夜,润物细无声</a>
<audio src='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' controls="controls"></audio>

Mix-training without speaker-vector

  • Female & male

<a name = "Wav5">好雨知时节,当春乃发声,随风潜入夜,润物细无声</a>
<audio src='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' controls="controls"></audio>