Skip to content

Commit 987176e

Browse files
committed
feat: update speech demo report
1 parent 734d525 commit 987176e

File tree

1 file changed

+10
-8
lines changed

1 file changed

+10
-8
lines changed

tts_tech_report/index.html

Lines changed: 10 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -389,7 +389,8 @@ <h2 id="zero-shot-vs-one-shot-demonstrations">Zero-Shot vs. One-Shot Demonstrati
389389
<div class="article-block">
390390
<h2 id="multilingual-and-cross-lingual-capabilities-demonstrations">Multilingual and Cross-Lingual Capabilities
391391
Demonstrations</h2>
392-
<p>Speech-02-HD maintain high naturalness in less common languages while demonstrating significant advantages in
392+
<p>Speech-02-HD maintains high naturalness in less common languages while demonstrating significant advantages
393+
in
393394
Standard
394395
Chinese pronunciation accuracy.</p>
395396
<div class="scroll-wrapper" style="margin-top: 2rem;">
@@ -514,7 +515,8 @@ <h2 id="multilingual-and-cross-lingual-capabilities-demonstrations">Multilingual
514515
</tbody>
515516
</table>
516517
</div>
517-
<div class="scroll-wrapper" style="margin-top: 3rem;">
518+
<p style="margin-top: 4rem;">Speech-02-HD has superior performance in zero-shot cross-lingual scenarios.</p>
519+
<div class="scroll-wrapper" style="margin-top: 2rem;">
518520
<table style="width: 100%;">
519521
<tbody>
520522
<tr class="border-bottom-thin">
@@ -528,7 +530,7 @@ <h2 id="multilingual-and-cross-lingual-capabilities-demonstrations">Multilingual
528530
</tr>
529531
<tr class="border-bottom-thin">
530532
<th>English</th>
531-
<td>Mandarin</td>
533+
<th>Mandarin</th>
532534
<td>
533535
<audio class="audio-sm" src="assets/audios/Wong_Sourse.mp3" controls></audio>
534536
</td>
@@ -551,7 +553,7 @@ <h2 id="multilingual-and-cross-lingual-capabilities-demonstrations">Multilingual
551553
</tr>
552554
<tr class="border-bottom-thin">
553555
<th>Mandarin</th>
554-
<td>Cantonese</td>
556+
<th>Cantonese</th>
555557
<td>
556558
<audio class="audio-sm" src="assets/audios/ShiBanYu_Sourse.mp3" controls></audio>
557559
</td>
@@ -572,7 +574,7 @@ <h2 id="multilingual-and-cross-lingual-capabilities-demonstrations">Multilingual
572574
</tr>
573575
<tr class="border-bottom-thin">
574576
<th>Mandarin</th>
575-
<td>English</td>
577+
<th>English</th>
576578
<td>
577579
<audio class="audio-sm" src="assets/audios/ShuanQ_Sourse.mp3" controls></audio>
578580
</td>
@@ -593,7 +595,7 @@ <h2 id="multilingual-and-cross-lingual-capabilities-demonstrations">Multilingual
593595
</tr>
594596
<tr class="border-bottom-thin">
595597
<th>English</th>
596-
<td>Spanish</td>
598+
<th>Spanish</th>
597599
<td>
598600
<audio class="audio-sm" src="assets/audios/CoCo_Sourse.mp3" controls></audio>
599601
</td>
@@ -614,7 +616,7 @@ <h2 id="multilingual-and-cross-lingual-capabilities-demonstrations">Multilingual
614616
</tr>
615617
<tr class="border-bottom-thin">
616618
<th>Japanese</th>
617-
<td>Korean</td>
619+
<th>Korean</th>
618620
<td>
619621
<audio class="audio-sm" src="assets/audios/Powerful_Girl_Sourse.mp3" controls></audio>
620622
</td>
@@ -773,7 +775,7 @@ <h3>DEMO</h3>
773775
<th scope="col">Neutral</th>
774776
<th scope="col" style="min-width: 120px;">Emotion</th>
775777
<th scope="col">Text</th>
776-
<th scope="col">Emotion-Infused Audio</th>
778+
<th scope="col">Emotion Control Audio</th>
777779
</tr>
778780
<tr class="border-bottom-thin">
779781
<td>

0 commit comments

Comments
 (0)