From d1ee10be102263da5fbfac1e131c31ed605b5ad0 Mon Sep 17 00:00:00 2001
From: chrisxu2016 <823254351@qq.com>
Date: Fri, 16 Jun 2017 18:29:56 +0800
Subject: [PATCH] modify audio and speech

---
 data_utils/audio.py  | 14 ++++++++------
 data_utils/speech.py | 26 ++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/data_utils/audio.py b/data_utils/audio.py
index ee4e6d84..066437dc 100755
--- a/data_utils/audio.py
+++ b/data_utils/audio.py
@@ -104,7 +104,8 @@ class AudioSegment(object):
             io.BytesIO(bytes), dtype='float32')
         return cls(samples, sample_rate)
 
-    def concatenate(self, *segments):
+    @classmethod
+    def concatenate(cls, *segments):
         """Concatenate an arbitrary number of audio segments together.
 
         :param *segments: Input audio segments
@@ -123,11 +124,11 @@ class AudioSegment(object):
             if sample_rate != seg._sample_rate:
                 raise ValueError("Can't concatenate segments with "
                                  "different sample rates")
-            if type(seg) is not type(self):
+            if type(seg) is not cls:
                 raise TypeError("Only audio segments of the same type "
                                 "instance can be concatenated.")
         samples = np.concatenate([seg.samples for seg in segments])
-        return type(self)(samples, sample_rate)
+        return cls(samples, sample_rate)
 
     def to_wav_file(self, filepath, dtype='float32'):
         """Save audio segment to disk as wav file.
@@ -355,13 +356,14 @@ class AudioSegment(object):
         """
         if duration == 0.0:
             return self
+        cls = type(self)
         silence = self.make_silence(duration, self._sample_rate)
         if sides == "beginning":
-            padded = self.concatenate(silence, self)
+            padded = cls.concatenate(silence, self)
         elif sides == "end":
-            padded = self.concatenate(self, silence)
+            padded = cls.concatenate(self, silence)
         elif sides == "both":
-            padded = self.concatenate(silence, self, silence)
+            padded = cls.concatenate(silence, self, silence)
         else:
             raise ValueError("Unknown value for the kwarg %s" % sides)
         self._samples = padded._samples
diff --git a/data_utils/speech.py b/data_utils/speech.py
index 48db595b..5d1fc15a 100755
--- a/data_utils/speech.py
+++ b/data_utils/speech.py
@@ -65,6 +65,32 @@ class SpeechSegment(AudioSegment):
         audio = AudioSegment.from_bytes(bytes)
         return cls(audio.samples, audio.sample_rate, transcript)
 
+    @classmethod
+    def concatenate(cls, *segments):
+        """Concatenate an arbitrary number of audio segments together.
+
+        :param *segments: Input speech segments
+        :type *segments: SpeechSegment
+        :return: Speech segment instance.
+        :rtype: SpeechSegment
+        :raises ValueError: If number of segments is zero, or if sample_rate
+                            not match between two audio segments
+        :raises TypeError: If item of segments is not Audiosegment instance
+        """
+        # Perform basic sanity-checks.
+        if len(segments) == 0:
+            raise ValueError("No audio segments are given to concatenate.")
+        sample_rate = segments[0]._sample_rate
+        for seg in segments:
+            if sample_rate != seg._sample_rate:
+                raise ValueError("Can't concatenate segments with "
+                                 "different sample rates")
+            if type(seg) is not cls:
+                raise TypeError("Only speech segments of the same type "
+                                "instance can be concatenated.")
+        samples = np.concatenate([seg.samples for seg in segments])
+        return cls(samples, sample_rate, seg._transcript)
+
     @property
     def transcript(self):
         """Return the transcript text.