“TTS-project-synthesis”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第79行: 第79行:
 
::*(10) 0.9:0.1 [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/roobo.child/mix-emotion-angry-neutral_1_9_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]
 
::*(10) 0.9:0.1 [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/roobo.child/mix-emotion-angry-neutral_1_9_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]
 
::*(11) 1.0:0.0 [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/roobo.child/x-angry_1_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]
 
::*(11) 1.0:0.0 [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/roobo.child/x-angry_1_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]
 +
 +
==Multi-speaker Multi-emotion==
 +
*Synthesis text:'据了解,天津市今年粮食种植面积达六百万亩,预计全年粮食总产量可达二十公斤,比去年提高了'
 +
:* female-angry [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/mix/female01.angry_1_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]
 +
:* female-happy [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/mix/female01.happy_1_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]
 +
:* female-neutral [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/mix/female01.neutral_1_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]
 +
:* female-sorrow [http://zhangzy.cslt.org/categories/tts/sample-wav/mimic-wangd-front-end/emotion/mix/female01.sorrow_1_amdurTanh_acTanh_mlpg1_postfilter1.world.wav01.wav]

2017年12月1日 (五) 03:48的版本

Project name

Text To Speech

Project members

Dong Wang, Zhiyong Zhang

Introduction

Text To Speech

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

Multi-speaker mix-trainingr

Without Speaker-vector

  • Female & Male[4]
  • Female & Child[5]
  • Male & Child[6]


With speaker-vector

When synthesis, we just replace the speaker-vector for specific person.

  • Specific person===
  • Interpolate the speaker-vector of different person
  • Female & Male with different ratio
  • (1) 0.0:1.0[9]

Mono-speaker Emotion TTS

  • Specific emotion
  • Neutral emotion [20]
  • Happy emotion [21]
  • Sorrow emotion [22]
  • Angry emotion [23]
  • Interpolation emotion
  • Angry & neutral with different ratio

Multi-speaker Multi-emotion

  • Synthesis text:'据了解,天津市今年粮食种植面积达六百万亩,预计全年粮食总产量可达二十公斤,比去年提高了'