Skip to content

tailMs and consonant duration limit #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 17, 2023
Merged

tailMs and consonant duration limit #10

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions OpenUtau.Core/DiffSinger/DiffSingerMandarinPhonemizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,10 +71,14 @@ public override Result Process(Note[] notes, Note? prev, Note? next, Note? prevN
//使用vogen的辅音时间
Result VogenResult = base.Process(notes, prev, next, prevNeighbour, nextNeighbour, prevs);
//辅音长度至少为1帧
int consonantPos = Math.Min(VogenResult.phonemes[0].position, -frameTick);
//辅音长度不能超过上一音符时长的2/3
if (prevNeighbour != null) {
consonantPos = Math.Max(consonantPos, -prevNeighbour.Value.duration * 2 / 3);
}
return new Result {
phonemes = new Phoneme[] {
new Phoneme {phoneme = phones.Item1,
position = Math.Min(VogenResult.phonemes[0].position,-frameTick)},
new Phoneme {phoneme = phones.Item1, position = consonantPos},
new Phoneme {phoneme = phones.Item2, position = 0}
},
};
Expand Down
8 changes: 5 additions & 3 deletions OpenUtau.Core/DiffSinger/DiffSingerRenderer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
namespace OpenUtau.Core.DiffSinger {
public class DiffSingerRenderer : IRenderer {
const float headMs = 0;
const float tailMs = 0;
const float tailMs = 500;

static readonly HashSet<string> supportedExp = new HashSet<string>(){
Format.Ustx.DYN,
Expand Down Expand Up @@ -109,10 +109,12 @@ float[] InvokeDiffsinger(RenderPhrase phrase,int speedup) {
//speedup：加速倍数
var tokens = phrase.phones
.Select(p => p.phoneme)
.Append("SP")
.Select(x => (long)(singer.phonemes.IndexOf(x)))
.ToList();
var durations = phrase.phones
.Select(p => (long)(p.endMs / frameMs) - (long)(p.positionMs / frameMs))//防止累计误差
.Append(tailFrames)
.ToList();
var totalFrames = (int)(durations.Sum());
var f0 = SampleCurve(phrase, phrase.pitches, 0, totalFrames, headFrames, tailFrames, x => MusicMath.ToneToFreq(x * 0.01));
Expand Down Expand Up @@ -167,8 +169,8 @@ double[] SampleCurve(RenderPhrase phrase, float[] curve, double defaultValue, in
}
}
//填充头尾
Array.Fill(result, defaultValue, 0, headFrames);
Array.Fill(result, defaultValue, length - tailFrames, tailFrames);
Array.Fill(result, convert(curve[0]), 0, headFrames);
Array.Fill(result, convert(curve.Last()), length - tailFrames, tailFrames);
return result;
}

Expand Down