[src] Making ivector extractor tolerate dim mismatch due to pitch (ka…

…ldi-asr#3727)
danpovey · Nov 21, 2019 · 59255ae · 59255ae
1 parent 249e2b2
commit 59255ae
Show file tree

Hide file tree

Showing 3 changed files with 21 additions and 1 deletion.
diff --git a/src/online2/online-ivector-feature.cc b/src/online2/online-ivector-feature.cc
@@ -67,6 +67,13 @@ void OnlineIvectorExtractionInfo::Init(
   this->Check();
 }
 
+int32 OnlineIvectorExtractionInfo::ExpectedFeatureDim() const {
+  int32 num_splice = 1 + splice_opts.left_context + splice_opts.right_context,
+      full_dim = diag_ubm.Dim();
+  KALDI_ASSERT(full_dim % num_splice == 0 &&
+               "Something went wrong getting the feature dimension");
+  return full_dim / num_splice;
+}
 
 void OnlineIvectorExtractionInfo::Check() const {
   KALDI_ASSERT(global_cmvn_stats.NumRows() == 2);

diff --git a/src/online2/online-ivector-feature.h b/src/online2/online-ivector-feature.h
@@ -193,6 +193,8 @@ struct OnlineIvectorExtractionInfo {
 
   void Init(const OnlineIvectorExtractionConfig &config);
 
+  int32 ExpectedFeatureDim() const;
+
   // This constructor creates a version of this object where everything
   // is empty or zero.
   OnlineIvectorExtractionInfo();

diff --git a/src/online2bin/ivector-extract-online2.cc b/src/online2bin/ivector-extract-online2.cc
@@ -94,6 +94,7 @@ int main(int argc, char *argv[]) {
     RandomAccessBaseFloatVectorReader frame_weights_reader(frame_weights_rspecifier);
     BaseFloatMatrixWriter ivector_writer(ivectors_wspecifier);
 
+    bool warned_dim = false;
     for (; !spk2utt_reader.Done(); spk2utt_reader.Next()) {
       std::string spk = spk2utt_reader.Key();
       const std::vector<std::string> &uttlist = spk2utt_reader.Value();
@@ -108,7 +109,17 @@ int main(int argc, char *argv[]) {
         }
         const Matrix<BaseFloat> &feats = feature_reader.Value(utt);
 
-        OnlineMatrixFeature matrix_feature(feats);
+        int32 feat_dim = feats.NumCols();
+        if (feat_dim == ivector_info.ExpectedFeatureDim() + 3) {
+          if (!warned_dim) {
+            KALDI_WARN << "Feature dimension is too large by 3, assuming there are "
+                "pitch features and removing the last 3 dims.";
+            warned_dim = true;
+          }
+          feat_dim -= 3;
+        }
+
+        OnlineMatrixFeature matrix_feature(feats.ColRange(0, feat_dim));
 
         OnlineIvectorFeature ivector_feature(ivector_info,
                                              &matrix_feature);