audio: interpolate audio timestamps

Deal with jittering Matroska crap timestamps. This reuses the mechanism
that is needed for frames without PTS, and adds a heuristic to it. If
the interpolated timestamp is less than 1ms away from the real one, it
might be due to Matroska timestamp rounding (or other file formats with
such rounding, or files remuxed from Matroska).

While there actually isn't much of a need to do this (audio PTS
jittering by such a low amount doesn't negatively influence much), it
helps with identifying jitter from other sources.

1 files changed, 12 insertions, 2 deletions

diff --git a/audio/decode/dec_audio.c b/audio/decode/dec_audio.c
index 623951eb22..98fb83f895 100644
--- a/audio/decode/dec_audio.c
+++ b/audio/decode/dec_audio.c
@@ -172,8 +172,18 @@ static int decode_new_frame(struct dec_audio *da)
 
         if (da->waiting) {
             if (da->waiting->pts != MP_NOPTS_VALUE) {
-                da->pts = da->waiting->pts;
-                da->pts_offset = 0;
+                if (da->pts != MP_NOPTS_VALUE) {
+                    da->pts += da->pts_offset / (double)da->waiting->rate;
+                    da->pts_offset = 0;
+                }
+                // Keep the interpolated timestamp if it doesn't deviate more
+                // than 1 ms from the real one. (MKV rounded timestamps.)
+                if (da->pts == MP_NOPTS_VALUE || da->pts_offset != 0 ||
+                    fabs(da->pts - da->waiting->pts) > 0.001)
+                {
+                    da->pts = da->waiting->pts;
+                    da->pts_offset = 0;
+                }
             }
             da->pts_offset += da->waiting->samples;
             da->decode_format = *da->waiting;