Skip to content

Commit

Permalink
update demo page
Browse files Browse the repository at this point in the history
  • Loading branch information
ming024 committed Oct 31, 2020
1 parent 491681a commit a0bc228
Showing 1 changed file with 250 additions and 1 deletion.
251 changes: 250 additions & 1 deletion docs/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,255 @@ <h4>Pair 1</h4>

</dl>

<h4>Pair 2</h4>
<dl class="row">
<dt class="col-sm-3">
Source speaker
</dt>
<dd class="col-sm-9">
p227
</dd>

<dt class="col-sm-3">
Target speaker
</dt>
<dd class="col-sm-9">
p225
</dd>

<dt class="col-sm-3">
Transcription
</dt>
<dd class="col-sm-9">
&#8220;
Many complicated ideas about the rainbow have been formed.
&#8221;
</dd>

<dt class="col-sm-3">
Source utterance
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/p227_020.wav">
Your browser does not support the audio tag!
</audio>
</dd>

<dt class="col-sm-3">
Authentic utterance
<br>
<small>
from the target speaker
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/p225_020.wav">
Your browser does not support the audio tag!
</audio>
</dd>

<dt class="col-sm-3">
Conversion result
<br>
<small>
with the authentic utterance as target
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/s2s-m2f-p227_020-p225_020.wav">
Your browser does not support the audio tag!
</audio>
<br>
<img src="imgs/p227_p225/s2s-m2f-p227_020-p225_020.attn.png">
</dd>

<dt class="col-sm-3">
Conversion result
<br>
<small>
with 5 randomly sampled target utterances
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/s2s-m2f-p227_020-p225_001_010_027_030_038.wav">
Your browser does not support the audio tag!
</audio>
<br>
<img src="imgs/p227_p225/s2s-m2f-p227_020-p225_001_010_027_030_038.attn.png">
</dd>

</dl>

<h4>Pair 3</h4>
<dl class="row">
<dt class="col-sm-3">
Source speaker
</dt>
<dd class="col-sm-9">
p228
</dd>

<dt class="col-sm-3">
Target speaker
</dt>
<dd class="col-sm-9">
p232
</dd>

<dt class="col-sm-3">
Transcription
</dt>
<dd class="col-sm-9">
&#8220;
Many complicated ideas about the rainbow have been formed.
&#8221;
</dd>

<dt class="col-sm-3">
Source utterance
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/p228_020.wav">
Your browser does not support the audio tag!
</audio>
</dd>

<dt class="col-sm-3">
Authentic utterance
<br>
<small>
from the target speaker
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/p232_020.wav">
Your browser does not support the audio tag!
</audio>
</dd>

<dt class="col-sm-3">
Conversion result
<br>
<small>
with the authentic utterance as target
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/s2s-f2m-p228_020-p232_020.wav">
Your browser does not support the audio tag!
</audio>
<br>
<img src="imgs/p228_p232/s2s-f2m-p228_020-p232_020.attn.png">
</dd>

<dt class="col-sm-3">
Conversion result
<br>
<small>
with 5 randomly sampled target utterances
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/s2s-f2m-p228_020-p232_001_010_027_030_038.wav">
Your browser does not support the audio tag!
</audio>
<br>
<img src="imgs/p228_p232/s2s-f2m-p228_020-p232_001_010_027_030_038.attn.png">
</dd>

</dl>

<h4>Pair 4</h4>
<dl class="row">
<dt class="col-sm-3">
Source speaker
</dt>
<dd class="col-sm-9">
p232
</dd>

<dt class="col-sm-3">
Target speaker
</dt>
<dd class="col-sm-9">
p228
</dd>

<dt class="col-sm-3">
Transcription
</dt>
<dd class="col-sm-9">
&#8220;
Ask her to bring these things with her from the store.
&#8221;
</dd>

<dt class="col-sm-3">
Source utterance
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/p232_002.wav">
Your browser does not support the audio tag!
</audio>
</dd>

<dt class="col-sm-3">
Authentic utterance
<br>
<small>
from the target speaker
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/p228_002.wav">
Your browser does not support the audio tag!
</audio>
</dd>

<dt class="col-sm-3">
Conversion result
<br>
<small>
with the authentic utterance as target
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/s2s-m2f-p232_002-p228_002.wav">
Your browser does not support the audio tag!
</audio>
<br>
<img src="imgs/p232_p228/s2s-m2f-p232_002-p228_002.attn.png">
</dd>

<dt class="col-sm-3">
Conversion result
<br>
<small>
with 5 randomly sampled target utterances
</small>
</dt>
<dd class="col-sm-9">
<audio controls>
<source src="wavs/s2s-m2f-p232_002-p228_001_010_025_052_090.wav">
Your browser does not support the audio tag!
</audio>
<br>
<img src="imgs/p232_p228/s2s-m2f-p232_002-p228_001_010_025_052_090.attn.png">
</dd>

</dl>

<!-- <h3>Unseen-to-unseen conversion</h3>
In the following sections, there are 4 conversion pairs, each containing 4 speech utterances.
Expand All @@ -175,4 +424,4 @@ <h4>Pair 1</h4>
</div>
</body>

</html>
</html>

0 comments on commit a0bc228

Please sign in to comment.