diff --git a/libavformat/isom.h b/libavformat/isom.h
index f3a7a8633d..e629663949 100644
--- a/libavformat/isom.h
+++ b/libavformat/isom.h
@@ -218,6 +218,7 @@ typedef struct MOVStreamContext {
     int *extradata_size;
     int last_stsd_index;
     int stsd_count;
+    int stsd_version;
 
     int32_t *display_matrix;
     AVStereo3D *stereo3d;
diff --git a/libavformat/mov.c b/libavformat/mov.c
index 02c8ec66ed..ec57a05803 100644
--- a/libavformat/mov.c
+++ b/libavformat/mov.c
@@ -2122,8 +2122,8 @@ static void mov_parse_stsd_audio(MOVContext *c, AVIOContext *pb,
     // Read QT version 1 fields. In version 0 these do not exist.
     av_log(c->fc, AV_LOG_TRACE, "version =%d, isom =%d\n", version, c->isom);
     if (!c->isom ||
-        (compatible_brands && strstr(compatible_brands->value, "qt  "))) {
-
+        (compatible_brands && strstr(compatible_brands->value, "qt  ")) ||
+        (sc->stsd_version == 0 && version > 0)) {
         if (version == 1) {
             sc->samples_per_frame = avio_rb32(pb);
             avio_rb32(pb); /* bytes per packet */
@@ -2554,7 +2554,7 @@ static int mov_read_stsd(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     st = c->fc->streams[c->fc->nb_streams - 1];
     sc = st->priv_data;
 
-    avio_r8(pb); /* version */
+    sc->stsd_version = avio_r8(pb);
     avio_rb24(pb); /* flags */
     entries = avio_rb32(pb);