Merge pull request #140 from xinghai-sun/noise

Add NoisePerturbAugmentor and CHiME3 noise data preparation.

deep_speech_2/conf/augmentation.config

+[
+    {
+        "type": "shift",
+        "params": {"min_shift_ms": -5,
+                   "max_shift_ms": 5},
+        "prob": 1.0
+    }
+]

deep_speech_2/conf/augmentation.config.example

+[
+    {
+        "type": "noise",
+        "params": {"min_snr_dB": 40,
+                   "max_snr_dB": 50,
+                   "noise_manifest_path": "datasets/manifest.noise"},
+        "prob": 0.6
+    },
+    {
+        "type": "impulse",
+        "params": {"impulse_manifest_path": "datasets/manifest.impulse"},
+        "prob": 0.5
+    },
+    {
+        "type": "speed",
+        "params": {"min_speed_rate": 0.95,
+                   "max_speed_rate": 1.05},
+        "prob": 0.5
+    },
+    {
+        "type": "shift",
+        "params": {"min_shift_ms": -5,
+                   "max_shift_ms": 5},
+        "prob": 1.0
+    },
+    {
+        "type": "volume",
+        "params": {"min_gain_dBFS": -10,
+                   "max_gain_dBFS": 10},
+        "prob": 0.0
+    },
+    {
+        "type": "bayesian_normal",
+        "params": {"target_db": -20,
+                   "prior_db": -20,
+                   "prior_samples": 100},
+        "prob": 0.0
+    }
+]

deep_speech_2/data_utils/audio.py

@@ -204,7 +204,7 @@ class AudioSegment(object):
         :raise ValueError: If the sample rates of the two segments are not
                            equal, or if the lengths of segments don't match.
         """
-        if type(self) != type(other):
+        if isinstance(other, type(self)):
             raise TypeError("Cannot add segments of different types: %s "
                             "and %s." % (type(self), type(other)))
         if self._sample_rate != other._sample_rate:
@@ -231,7 +231,7 @@ class AudioSegment(object):
         Note that this is an in-place transformation.
         
         :param gain: Gain in decibels to apply to samples. 
-        :type gain: float
+        :type gain: float|1darray
         """
         self._samples *= 10.**(gain / 20.)
 
@@ -457,9 +457,9 @@ class AudioSegment(object):
                             audio segments when resample is not allowed.
         """
         if allow_resample and self.sample_rate != impulse_segment.sample_rate:
-            impulse_segment = impulse_segment.resample(self.sample_rate)
+            impulse_segment.resample(self.sample_rate)
         if self.sample_rate != impulse_segment.sample_rate:
-            raise ValueError("Impulse segment's sample rate (%d Hz) is not"
+            raise ValueError("Impulse segment's sample rate (%d Hz) is not "
                              "equal to base signal sample rate (%d Hz)." %
                              (impulse_segment.sample_rate, self.sample_rate))
         samples = signal.fftconvolve(self.samples, impulse_segment.samples,

deep_speech_2/data_utils/augmentor/augmentation.py

@@ -8,6 +8,8 @@ import random
 from data_utils.augmentor.volume_perturb import VolumePerturbAugmentor
 from data_utils.augmentor.shift_perturb import ShiftPerturbAugmentor
 from data_utils.augmentor.speed_perturb import SpeedPerturbAugmentor
+from data_utils.augmentor.noise_perturb import NoisePerturbAugmentor
+from data_utils.augmentor.impulse_response import ImpulseResponseAugmentor
 from data_utils.augmentor.resample import ResampleAugmentor
 from data_utils.augmentor.online_bayesian_normalization import \
      OnlineBayesianNormalizationAugmentor
@@ -23,21 +25,46 @@ class AugmentationPipeline(object):
     string, e.g.
     
     .. code-block::
-        
-        '[{"type": "volume",
-           "params": {"min_gain_dBFS": -15,
-                      "max_gain_dBFS": 15},
-           "prob": 0.5},
-          {"type": "speed",
-           "params": {"min_speed_rate": 0.8,
-                      "max_speed_rate": 1.2},
-           "prob": 0.5}
-         ]' 
 
+        [ {
+                "type": "noise",
+                "params": {"min_snr_dB": 10,
+                           "max_snr_dB": 20,
+                           "noise_manifest_path": "datasets/manifest.noise"},
+                "prob": 0.0
+            },
+            {
+                "type": "speed",
+                "params": {"min_speed_rate": 0.9,
+                           "max_speed_rate": 1.1},
+                "prob": 1.0
+            },
+            {
+                "type": "shift",
+                "params": {"min_shift_ms": -5,
+                           "max_shift_ms": 5},
+                "prob": 1.0
+            },
+            {
+                "type": "volume",
+                "params": {"min_gain_dBFS": -10,
+                           "max_gain_dBFS": 10},
+                "prob": 0.0
+            },
+            {
+                "type": "bayesian_normal",
+                "params": {"target_db": -20,
+                           "prior_db": -20,
+                           "prior_samples": 100},
+                "prob": 0.0
+            }
+        ]
+        
     This augmentation configuration inserts two augmentation models
     into the pipeline, with one is VolumePerturbAugmentor and the other
     SpeedPerturbAugmentor. "prob" indicates the probability of the current
-    augmentor to take effect.
+    augmentor to take effect. If "prob" is zero, the augmentor does not take
+    effect.
 
     :param augmentation_config: Augmentation configuration in json string.
     :type augmentation_config: str
@@ -60,7 +87,7 @@ class AugmentationPipeline(object):
         :type audio_segment: AudioSegmenet|SpeechSegment
         """
         for augmentor, rate in zip(self._augmentors, self._rates):
-            if self._rng.uniform(0., 1.) <= rate:
+            if self._rng.uniform(0., 1.) < rate:
                 augmentor.transform_audio(audio_segment)
 
     def _parse_pipeline_from(self, config_json):
@@ -89,5 +116,9 @@ class AugmentationPipeline(object):
             return ResampleAugmentor(self._rng, **params)
         elif augmentor_type == "bayesian_normal":
             return OnlineBayesianNormalizationAugmentor(self._rng, **params)
+        elif augmentor_type == "noise":
+            return NoisePerturbAugmentor(self._rng, **params)
+        elif augmentor_type == "impulse":
+            return ImpulseResponseAugmentor(self._rng, **params)
         else:
             raise ValueError("Unknown augmentor type [%s]." % augmentor_type)

deep_speech_2/data_utils/augmentor/impulse_response.py

+"""Contains the impulse response augmentation model."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from data_utils.augmentor.base import AugmentorBase
+from data_utils import utils
+from data_utils.audio import AudioSegment
+
+
+class ImpulseResponseAugmentor(AugmentorBase):
+    """Augmentation model for adding impulse response effect.
+    
+    :param rng: Random generator object.
+    :type rng: random.Random
+    :param impulse_manifest_path: Manifest path for impulse audio data.
+    :type impulse_manifest_path: basestring 
+    """
+
+    def __init__(self, rng, impulse_manifest_path):
+        self._rng = rng
+        self._impulse_manifest = utils.read_manifest(
+            manifest_path=impulse_manifest_path)
+
+    def transform_audio(self, audio_segment):
+        """Add impulse response effect.
+
+        Note that this is an in-place transformation.
+
+        :param audio_segment: Audio segment to add effects to.
+        :type audio_segment: AudioSegmenet|SpeechSegment
+        """
+        impulse_json = self._rng.sample(self._impulse_manifest, 1)[0]
+        impulse_segment = AudioSegment.from_file(impulse_json['audio_filepath'])
+        audio_segment.convolve(impulse_segment, allow_resample=True)

deep_speech_2/data_utils/augmentor/noise_perturb.py

+"""Contains the noise perturb augmentation model."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from data_utils.augmentor.base import AugmentorBase
+from data_utils import utils
+from data_utils.audio import AudioSegment
+
+
+class NoisePerturbAugmentor(AugmentorBase):
+    """Augmentation model for adding background noise.
+    
+    :param rng: Random generator object.
+    :type rng: random.Random
+    :param min_snr_dB: Minimal signal noise ratio, in decibels.
+    :type min_snr_dB: float
+    :param max_snr_dB: Maximal signal noise ratio, in decibels.
+    :type max_snr_dB: float
+    :param noise_manifest_path: Manifest path for noise audio data.
+    :type noise_manifest_path: basestring 
+    """
+
+    def __init__(self, rng, min_snr_dB, max_snr_dB, noise_manifest_path):
+        self._min_snr_dB = min_snr_dB
+        self._max_snr_dB = max_snr_dB
+        self._rng = rng
+        self._noise_manifest = utils.read_manifest(
+            manifest_path=noise_manifest_path)
+
+    def transform_audio(self, audio_segment):
+        """Add background noise audio.
+
+        Note that this is an in-place transformation.
+
+        :param audio_segment: Audio segment to add effects to.
+        :type audio_segment: AudioSegmenet|SpeechSegment
+        """
+        noise_json = self._rng.sample(self._noise_manifest, 1)[0]
+        if noise_json['duration'] < audio_segment.duration:
+            raise RuntimeError("The duration of sampled noise audio is smaller "
+                               "than the audio segment to add effects to.")
+        diff_duration = noise_json['duration'] - audio_segment.duration
+        start = self._rng.uniform(0, diff_duration)
+        end = start + audio_segment.duration
+        noise_segment = AudioSegment.slice_from_file(
+            noise_json['audio_filepath'], start=start, end=end)
+        snr_dB = self._rng.uniform(self._min_snr_dB, self._max_snr_dB)
+        audio_segment.add_noise(
+            noise_segment, snr_dB, allow_downsampling=True, rng=self._rng)

deep_speech_2/data_utils/data.py

@@ -169,7 +169,7 @@ class DataGenerator(object):
                         manifest, batch_size, clipped=True)
                 elif shuffle_method == "instance_shuffle":
                     self._rng.shuffle(manifest)
-                elif not shuffle_method:
+                elif shuffle_method == None:
                     pass
                 else:
                     raise ValueError("Unknown shuffle method %s." %

deep_speech_2/data_utils/speech.py

@@ -115,7 +115,7 @@ class SpeechSegment(AudioSegment):
                  speech file.
         :rtype: SpeechSegment
         """
-        audio = Audiosegment.slice_from_file(filepath, start, end)
+        audio = AudioSegment.slice_from_file(filepath, start, end)
         return cls(audio.samples, audio.sample_rate, transcript)
 
     @classmethod

deep_speech_2/datasets/noise/chime3_background.py

+"""Prepare CHiME3 background data.
+
+Download, unpack and create manifest files.
+Manifest file is a json-format file with each line containing the
+meta data (i.e. audio filepath, transcript and audio duration)
+of each audio file in the data set.
+"""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import distutils.util
+import os
+import wget
+import zipfile
+import argparse
+import soundfile
+import json
+from paddle.v2.dataset.common import md5file
+
+DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset/speech')
+
+URL = "https://d4s.myairbridge.com/packagev2/AG0Y3DNBE5IWRRTV/?dlid=W19XG7T0NNHB027139H0EQ"
+MD5 = "c3ff512618d7a67d4f85566ea1bc39ec"
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--target_dir",
+    default=DATA_HOME + "/chime3_background",
+    type=str,
+    help="Directory to save the dataset. (default: %(default)s)")
+parser.add_argument(
+    "--manifest_filepath",
+    default="manifest.chime3.background",
+    type=str,
+    help="Filepath for output manifests. (default: %(default)s)")
+args = parser.parse_args()
+
+
+def download(url, md5sum, target_dir, filename=None):
+    """Download file from url to target_dir, and check md5sum."""
+    if filename == None:
+        filename = url.split("/")[-1]
+    if not os.path.exists(target_dir): os.makedirs(target_dir)
+    filepath = os.path.join(target_dir, filename)
+    if not (os.path.exists(filepath) and md5file(filepath) == md5sum):
+        print("Downloading %s ..." % url)
+        wget.download(url, target_dir)
+        print("\nMD5 Chesksum %s ..." % filepath)
+        if not md5file(filepath) == md5sum:
+            raise RuntimeError("MD5 checksum failed.")
+    else:
+        print("File exists, skip downloading. (%s)" % filepath)
+    return filepath
+
+
+def unpack(filepath, target_dir):
+    """Unpack the file to the target_dir."""
+    print("Unpacking %s ..." % filepath)
+    if filepath.endswith('.zip'):
+        zip = zipfile.ZipFile(filepath, 'r')
+        zip.extractall(target_dir)
+        zip.close()
+    elif filepath.endswith('.tar') or filepath.endswith('.tar.gz'):
+        tar = zipfile.open(filepath)
+        tar.extractall(target_dir)
+        tar.close()
+    else:
+        raise ValueError("File format is not supported for unpacking.")
+
+
+def create_manifest(data_dir, manifest_path):
+    """Create a manifest json file summarizing the data set, with each line
+    containing the meta data (i.e. audio filepath, transcription text, audio
+    duration) of each audio file within the data set.
+    """
+    print("Creating manifest %s ..." % manifest_path)
+    json_lines = []
+    for subfolder, _, filelist in sorted(os.walk(data_dir)):
+        for filename in filelist:
+            if filename.endswith('.wav'):
+                filepath = os.path.join(data_dir, subfolder, filename)
+                audio_data, samplerate = soundfile.read(filepath)
+                duration = float(len(audio_data)) / samplerate
+                json_lines.append(
+                    json.dumps({
+                        'audio_filepath': filepath,
+                        'duration': duration,
+                        'text': ''
+                    }))
+    with open(manifest_path, 'w') as out_file:
+        for line in json_lines:
+            out_file.write(line + '\n')
+
+
+def prepare_chime3(url, md5sum, target_dir, manifest_path):
+    """Download, unpack and create summmary manifest file."""
+    if not os.path.exists(os.path.join(target_dir, "CHiME3")):
+        # download
+        filepath = download(url, md5sum, target_dir,
+                            "myairbridge-AG0Y3DNBE5IWRRTV.zip")
+        # unpack
+        unpack(filepath, target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_bus.zip'), target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_caf.zip'), target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_ped.zip'), target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_str.zip'), target_dir)
+    else:
+        print("Skip downloading and unpacking. Data already exists in %s." %
+              target_dir)
+    # create manifest json file
+    create_manifest(target_dir, manifest_path)
+
+
+def main():
+    prepare_chime3(
+        url=URL,
+        md5sum=MD5,
+        target_dir=args.target_dir,
+        manifest_path=args.manifest_filepath)
+
+
+if __name__ == '__main__':
+    main()

deep_speech_2/datasets/run_noise.sh

+cd noise 
+python chime3_background.py
+if [ $? -ne 0 ]; then
+    echo "Prepare CHiME3 background noise failed. Terminated."
+    exit 1
+fi
+cd -
+
+cat noise/manifest.* > manifest.noise
+echo "All done."

deep_speech_2/train.py

@@ -123,9 +123,7 @@ parser.add_argument(
     help="Directory for saving models. (default: %(default)s)")
 parser.add_argument(
     "--augmentation_config",
-    default='[{"type": "shift", '
-    '"params": {"min_shift_ms": -5, "max_shift_ms": 5},'
-    '"prob": 1.0}]',
+    default=open('conf/augmentation.config', 'r').read(),
     type=str,
     help="Augmentation configuration in json-format. "
     "(default: %(default)s)")