├── README.md
├── _config.yml
├── index.md
├── pics
└── structure.png
└── res
├── other
├── mini_gt.wav
├── mini_unet.wav
├── pause_gt.wav
├── pause_unet.wav
├── qsy_gt.wav
├── qsy_unet.wav
├── stress_gt.wav
└── stress_unet.wav
└── test
├── non-parallel
├── angry01_gst.wav
├── angry01_gt.wav
├── angry01_unet.wav
├── angry02_gst.wav
├── angry02_gt.wav
├── angry02_unet.wav
├── happy01_gst.wav
├── happy01_gt.wav
├── happy01_unet.wav
├── happy02_gst.wav
├── happy02_gt.wav
├── happy02_unet.wav
├── neutral01_gst.wav
├── neutral01_gt.wav
├── neutral01_unet.wav
├── neutral02_gst.wav
├── neutral02_gt.wav
├── neutral02_unet.wav
├── sad01_gst.wav
├── sad01_gt.wav
├── sad01_unet.wav
├── sad02_gst.wav
├── sad02_gt.wav
├── sad02_unet.wav
├── surprise01_gst.wav
├── surprise01_gt.wav
├── surprise01_unet.wav
├── surprise02_gst.wav
├── surprise02_gt.wav
└── surprise02_unet.wav
└── parallel
├── angry01_gst.wav
├── angry01_gt.wav
├── angry01_spk.wav
├── angry01_unet.wav
├── angry02_gst.wav
├── angry02_gt.wav
├── angry02_spk.wav
├── angry02_unet.wav
├── happy01_gst.wav
├── happy01_gt.wav
├── happy01_spk.wav
├── happy01_unet.wav
├── happy02_gst.wav
├── happy02_gt.wav
├── happy02_spk.wav
├── happy02_unet.wav
├── neutral01_gst.wav
├── neutral01_gt.wav
├── neutral01_spk.wav
├── neutral01_unet.wav
├── neutral02_gst.wav
├── neutral02_gt.wav
├── neutral02_spk.wav
├── neutral02_unet.wav
├── sad01_gst.wav
├── sad01_gt.wav
├── sad01_spk.wav
├── sad01_unet.wav
├── sad02_gst.wav
├── sad02_gt.wav
├── sad02_spk.wav
├── sad02_unet.wav
├── surprise01_gst.wav
├── surprise01_gt.wav
├── surprise01_spk.wav
├── surprise01_unet.wav
├── surprise02_gst.wav
├── surprise02_gt.wav
├── surprise02_spk.wav
└── surprise02_unet.wav
/README.md:
--------------------------------------------------------------------------------
1 | ## Unet-TTS: Improving Unseen Speaker and Style Transfer in One-shot Voice Cloning
2 | Email: rayn.li@cloudminds.com
3 |
4 | Our proposed algorithm has powerful speaker and style transfer capabilities, especially excellent imitation of out-of-domain emotions.
5 | - No fine-tuning required, just a few seconds of target audio
6 | - Synthesize arbitrary text
7 | - Embedding pause, stess, and other speaking styles in speech
8 |
9 | [Code](https://github.com/CMsmartvoice/One-Shot-Voice-Cloning)
10 |
11 | [Colab notebook](https://colab.research.google.com/drive/1sEDvKTJCY7uosb7TvTqwyUdwNPiv3pBW?usp=sharing)
12 |
13 | [Mandarin results](https://cmsmartvoice.github.io/Unet-TTS/)
14 |
15 | [Paper link](https://arxiv.org/abs/2109.11115)
16 |
17 | One-shot voice cloning aims to transform speaker voice and speaking style in speech synthesized from a text-to-speech (TTS) system, where only a shot recording from the target speech can be used. Out-of-domain transfer is still a challenging task, and one important aspect that impacts the accuracy and similarity of synthetic speech is the conditional representations carrying speaker or style cues extracted from the limited references. In this paper, we present a novel one-shot voice cloning algorithm called Unet-TTS that has good generalization ability for unseen speakers and styles. Based on a skip-connected U-net structure, the new model can efficiently discover speaker-level and utterance-level spectral feature details from the reference audio, enabling accurate inference of complex acoustic characteristics as well as imitation of speaking styles into the synthetic speech. According to both subjective and objective evaluations of similarity, the new model outperforms both speaker embedding and unsupervised style modeling (GST) approaches on an unseen emotional corpus.
18 |
19 | 
20 |
--------------------------------------------------------------------------------
/_config.yml:
--------------------------------------------------------------------------------
1 | theme: jekyll-theme-slate
--------------------------------------------------------------------------------
/index.md:
--------------------------------------------------------------------------------
1 | ---
2 | layout: default
3 | ---
4 |
5 | ## Unet-TTS: Improving Unseen Speaker and Style Transfer in One-shot Voice Cloning
6 | Email: rayn.li@cloudminds.com
7 |
8 | Our proposed algorithm has powerful speaker and style transfer capabilities, especially excellent imitation of out-of-domain emotions.
9 |
10 | - No fine-tuning required, just a few seconds of target audio
11 | - Synthesize arbitrary text
12 | - Embedding pause, stess, and other speaking styles in speech
13 |
14 | [Code](https://github.com/CMsmartvoice/One-Shot-Voice-Cloning)
15 |
16 | [Colab notebook](https://colab.research.google.com/drive/1sEDvKTJCY7uosb7TvTqwyUdwNPiv3pBW?usp=sharing)
17 |
18 | [Paper link](https://arxiv.org/abs/2109.11115)
19 |
20 | ## Abstract
21 | One-shot voice cloning aims to transform speaker voice and speaking style in speech synthesized from a text-to-speech (TTS) system, where only a shot recording from the target speech can be used. Out-of-domain transfer is still a challenging task, and one important aspect that impacts the accuracy and similarity of synthetic speech is the conditional representations carrying speaker or style cues extracted from the limited references. In this paper, we present a novel one-shot voice cloning algorithm called Unet-TTS that has good generalization ability for unseen speakers and styles. Based on a skip-connected U-net structure, the new model can efficiently discover speaker-level and utterance-level spectral feature details from the reference audio, enabling accurate inference of complex acoustic characteristics as well as imitation of speaking styles into the synthetic speech. According to both subjective and objective evaluations of similarity, the new model outperforms both speaker embedding and unsupervised style modeling (GST) approaches on an unseen emotional corpus.
22 |
23 | 
24 |
25 | ## Demo (One-shot Unseen Emotion Transfer)
26 |
27 | **Model Description:**
28 | **Unet-TTS** - Our proposed model
29 | **GST** - Tacotron with unsupervised style modeling of GST
30 | **SpkEmbed** - Tacotron with speaker embedding
31 |
32 | These reference emotion speech to be transferred are unseen in the training process.
33 |
34 | ## 1. Same Text as Reference
35 |
36 | #### Neutral
37 | - 七十六万八千四百四十四
38 |
39 | | Unet-TTS | GST | SpkEmbed |
40 | |:---------------: |:------------:|:--------------:|
41 | | | | |
42 |
43 | - 希望以后找个老师好好学一下
44 |
45 | | Unet-TTS | GST | SpkEmbed |
46 | |:---------------: |:------------:|:--------------:|
47 | | | | |
48 |
49 | #### Angry
50 | - 我不怎么在乎这个店有没有名
51 |
52 | | Unet-TTS | GST | SpkEmbed |
53 | |:---------------: |:------------:|:--------------:|
54 | | | | |
55 |
56 | - 我觉得并不是非要有特别的品质
57 |
58 | | Unet-TTS | GST | SpkEmbed |
59 | |:---------------: |:------------:|:--------------:|
60 | | | | |
61 |
62 | #### Surprise
63 | - 但是有时夏天比其它季节更迷人
64 |
65 | | Unet-TTS | GST | SpkEmbed |
66 | |:---------------: |:------------:|:--------------:|
67 | | | | |
68 |
69 | - 不管怎么说主队好象是志在夺魁
70 |
71 | | Unet-TTS | GST | SpkEmbed |
72 | |:---------------: |:------------:|:--------------:|
73 | | | | |
74 |
75 | #### Happy
76 | - 我必须再次感谢您的慷慨相助
77 |
78 | | Unet-TTS | GST | SpkEmbed |
79 | |:---------------: |:------------:|:--------------:|
80 | | | | |
81 |
82 | - 你女儿和她妈妈长得很像
83 |
84 | | Unet-TTS | GST | SpkEmbed |
85 | |:---------------: |:------------:|:--------------:|
86 | | | | |
87 |
88 | #### Sad
89 | - 你的身影总是在我心里晃来晃去
90 |
91 | | Unet-TTS | GST | SpkEmbed |
92 | |:---------------: |:------------:|:--------------:|
93 | | | | |
94 |
95 | - 你不应该害怕开始一段新的感情
96 |
97 | | Unet-TTS | GST | SpkEmbed |
98 | |:---------------: |:------------:|:--------------:|
99 | | | | |
100 |
101 |
102 | ## 2. Arbitrary Text (AT)
103 | **(The text of the reference is the same as above)**
104 |
105 | #### Neutral
106 | - AT1: 多地农村出现了空心化的趋势
107 | - AT2: 恰好成为可以互相参照的对象
108 |
109 | | Reference | Unet-TTS | GST |
110 | |:---------------: |:------------:|:--------------:|
111 | | | | |
112 | | | | |
113 |
114 | #### Angry
115 | - AT1: 本音频由一句话风格迁移语音合成系统合成
116 | - AT2: 这些颜色也不太适合你
117 |
118 | | Reference | Unet-TTS | GST |
119 | |:---------------: |:------------:|:--------------:|
120 | | | | |
121 | | | | |
122 |
123 | #### Surprise
124 | - AT1: 他讲的笑话让我笑个不停
125 | - AT2: 他们的配合值得我们学习
126 |
127 | | Reference | Unet-TTS | GST |
128 | |:---------------: |:------------:|:--------------:|
129 | | | | |
130 | | | | |
131 |
132 | #### Happy
133 | - AT1: 听起来你们玩得也很开心
134 | - AT2: 你们到底有完没完了
135 |
136 | | Reference | Unet-TTS | GST |
137 | |:---------------: |:------------:|:--------------:|
138 | | | | |
139 | | | | |
140 |
141 | #### Sad
142 | - AT1: 我只打算放松一下自己
143 | - AT2: 我知道人生并不总是一帆风顺
144 |
145 | | Reference | Unet-TTS | GST |
146 | |:---------------: |:------------:|:--------------:|
147 | | | | |
148 | | | | |
149 |
150 | ## 3. Other
151 | - Ref1: 我必须一直通电才能工作
152 | - Ref2: 就经常去我们宿舍附近的酒吧
153 | - Ref3: 产业园这是一个第一期的这个,第一期的这个,建筑面积应该是两百四十三亩
154 | - Ref4: 请问台湾居民能否使用旅游签证乘坐国内航班
155 |
156 | - AT: 本音频由一句话风格迁移语音合成系统合成
157 |
158 | | Description | Reference | Unet-TTS |
159 | |:---------------: |:------------:|:--------------:|
160 | | Pause style | | |
161 | | Stress style | | |
162 | | PC Recording | | |
163 | | Phone recording | | |
164 |
--------------------------------------------------------------------------------
/pics/structure.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/pics/structure.png
--------------------------------------------------------------------------------
/res/other/mini_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/mini_gt.wav
--------------------------------------------------------------------------------
/res/other/mini_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/mini_unet.wav
--------------------------------------------------------------------------------
/res/other/pause_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/pause_gt.wav
--------------------------------------------------------------------------------
/res/other/pause_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/pause_unet.wav
--------------------------------------------------------------------------------
/res/other/qsy_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/qsy_gt.wav
--------------------------------------------------------------------------------
/res/other/qsy_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/qsy_unet.wav
--------------------------------------------------------------------------------
/res/other/stress_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/stress_gt.wav
--------------------------------------------------------------------------------
/res/other/stress_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/other/stress_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/angry01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/angry01_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/angry01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/angry01_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/angry01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/angry01_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/angry02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/angry02_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/angry02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/angry02_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/angry02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/angry02_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/happy01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/happy01_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/happy01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/happy01_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/happy01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/happy01_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/happy02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/happy02_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/happy02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/happy02_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/happy02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/happy02_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/neutral01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/neutral01_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/neutral01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/neutral01_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/neutral01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/neutral01_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/neutral02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/neutral02_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/neutral02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/neutral02_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/neutral02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/neutral02_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/sad01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/sad01_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/sad01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/sad01_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/sad01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/sad01_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/sad02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/sad02_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/sad02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/sad02_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/sad02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/sad02_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/surprise01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/surprise01_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/surprise01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/surprise01_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/surprise01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/surprise01_unet.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/surprise02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/surprise02_gst.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/surprise02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/surprise02_gt.wav
--------------------------------------------------------------------------------
/res/test/non-parallel/surprise02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/non-parallel/surprise02_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry01_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry01_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry01_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry01_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry01_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry02_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry02_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry02_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry02_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/angry02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/angry02_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy01_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy01_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy01_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy01_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy01_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy02_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy02_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy02_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy02_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/happy02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/happy02_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral01_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral01_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral01_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral01_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral01_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral02_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral02_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral02_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral02_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/neutral02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/neutral02_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad01_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad01_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad01_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad01_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad01_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad02_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad02_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad02_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad02_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/sad02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/sad02_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise01_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise01_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise01_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise01_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise01_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise01_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise01_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise01_unet.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise02_gst.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise02_gst.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise02_gt.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise02_gt.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise02_spk.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise02_spk.wav
--------------------------------------------------------------------------------
/res/test/parallel/surprise02_unet.wav:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CMsmartvoice/Unet-TTS/38a58f574350512c83a894dcadd0613c83958b4e/res/test/parallel/surprise02_unet.wav
--------------------------------------------------------------------------------