I tried to recognize the wake word

What went

happy New Year. This is a hobby study record I went to during my New Year's homecoming.

Normally, when using the voice assistant, I think it's OK to call with a wake word such as Google. When I received Deep Learning Specialization (Coursera) by Dr. Andrew Ng There was an issue with implementing a model that detects wakeward utterances.

This article is a review of the above course, It is a record that generated learning data based on the recorded data of one's voice and trained it with the implemented model. There is little data and the results are simple, but eventually I would like to increase the data and improve the model to experiment.

Deep Learning Specialization is voluminous but easy to understand. I recommend it because I was able to understand it even as a beginner.

Execution environment

Creating training data

material

--Background noise.wav 2 types --Voice recording .wav --Two types of recordings of your own voice saying'TEST'(ground voice, falsetto)

Contents

--Defined a function to generate a large amount of learning data from a small amount of material --Randomly change the volume of noise, the location where voice is combined, and the number (1 to 3) to secure variation

--What you get --Input data X: Spectrogram of synthetic sound source for 10s (number of time frames, number of frequency bins) --Correct label y: 0 or 1 flag ――The label about 40ms after the part where the voice was synthesized was set to 1. The rest is 0

Generated data

--The above figure is a spectrogram that is input data (vertical: frequency [Hz] horizontal: time) ――The color of the corresponding part has changed due to the composition of the voice. ――This color shows the strength of the frequency component of the voice.

--The figure below shows the generated correct label. --The label of the combined part is changed to 1. --Attempts to infer this from the input data

Function for generation

A function defined for data generation

BACKGROUND_DIR = '/tmp/background'
VOICE_DIR = '/tmp/voice'
RATE = 12000
Ty = 117
TRAIN_DATA_LENGTH = int(10*RATE)

def make_train_sound(background, target, length, dumpwav=False):
    """
    arguments
    background: background noise data
    target: target sound data (will be added to background noise)
    length: sample length
    dumpwav: make wav data

    output
    X: spectrogram data  ( shape = (NFFT, frames))
    y: flag data (shap)
    """
    NFFT = 512
    FLAG_DULATION = 5
    TARGET_SYNTH_NUM = np.random.randint(1,high=3)
    
    # initialize
    train_sound = np.copy(background[:length])
    gain = np.random.random()
    train_sound *= gain
    target_length = len(target)
    y_size = Ty
    y = [0 for i in range(y_size)]

    # Synthesize
    for num in range(TARGET_SYNTH_NUM):
        # Decide where to add target into background noise
        range_start = int(length*num/TARGET_SYNTH_NUM)
        range_end = int(length*(num+1)/TARGET_SYNTH_NUM)
        synth_start_sample = np.random.randint(range_start, high=( range_end - target_length - FLAG_DULATION*(NFFT) ))
        # Add
        train_sound[synth_start_sample:synth_start_sample + target_length] += np.copy(target)
        
        # get Spectrogram
        specgram, freqs, t, img = plt.specgram(train_sound,NFFT=NFFT, Fs=RATE, noverlap=int(NFFT/2), scale="dB")
        X = specgram        # (freqs, time)

        # Labeling
        target_end_sec = (synth_start_sample+target_length)/RATE
        train_sound_sec = length/RATE
        flag_start_sample = int( ( target_end_sec / train_sound_sec ) * y_size)
        flag_end_sample = flag_start_sample+FLAG_DULATION
        if y_size <= flag_end_sample:
          over_length = flag_end_sample-y_size
          flag_end_sample -= over_length
          duration = FLAG_DULATION - over_length
        else:
          duration = FLAG_DULATION
        y[flag_start_sample:flag_end_sample] = [1 for i in range(duration)]

    if dumpwav:
        scipy.io.wavfile.write("train.wav", RATE, train_sound)

    y = np.array(y)
    return (X, y)

def make_train_pattern(pattern_num):
    """
    return list of training data
    [(X_1, y_1), (X_2, y_2) ... ]
    
    arguments
    pattern_num: Number of patterns (X, y)
    
    output:
    train_pattern: X input_data, y labels
        [(X_1, y_1), (X_2, y_2) ... ]
    """
    bg_items = get_item_list(BACKGROUND_DIR)
    voice_items = get_item_list(VOICE_DIR)

    train_pattern = []
    for i in range(pattern_num):
        item_no = get_item_no(bg_items)
        fs, bgdata = read(bg_items[item_no])

        item_no = get_item_no(voice_items)
        fs, voicedata = read(voice_items[item_no])
        pattern = make_train_sound(bgdata, voicedata, TRAIN_DATA_LENGTH, dumpwav=False)

        train_pattern.append(pattern)
    
    return train_pattern

--Using these, 1500 data were generated and separated for train, validation, and test. --Since 1500 or more have exceeded the RAM of Colab and stopped, so far --In order to handle the input data as time series data, the shape was changed (number of time frames, number of frequency bins).

#Data creation
train_patterns = make_train_pattern(1500)

#Input from the obtained tuple,Divide into correct labels
X = []
y = []
for t in train_patterns:
    X.append(t[0].T)    # (Time, Freq)
    y.append(t[1])
X = np.array(X)
y = np.array(y)[:,:,np.newaxis]

train_patterns = None

# training, validation,Divide for test
train_num = int(0.7*len(X))
val_num = int(0.2*len(X))
test_num = int(0.1*len(X))

X_train = X[:train_num]
y_train = y[:train_num]
X_validation = X[train_num:train_num+val_num]
y_validation = y[train_num:train_num+val_num]
X_test = X[train_num+val_num:]
y_test = y[train_num+val_num:]
train_data_shape = X_train[0].shape

Model for learning

--Defined a model with one layer of CNN and two layers of LSTM. --input_shape is set to the size of the training data (spectrogram)

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_6 (InputLayer)         (None, 467, 257)          0         
_________________________________________________________________
conv1d_6 (Conv1D)            (None, 117, 196)          755776    
_________________________________________________________________
batch_normalization_16 (Batc (None, 117, 196)          784       
_________________________________________________________________
activation_6 (Activation)    (None, 117, 196)          0         
_________________________________________________________________
dropout_16 (Dropout)         (None, 117, 196)          0         
_________________________________________________________________
cu_dnnlstm_11 (CuDNNLSTM)    (None, 117, 128)          166912    
_________________________________________________________________
batch_normalization_17 (Batc (None, 117, 128)          512       
_________________________________________________________________
dropout_17 (Dropout)         (None, 117, 128)          0         
_________________________________________________________________
cu_dnnlstm_12 (CuDNNLSTM)    (None, 117, 128)          132096    
_________________________________________________________________
batch_normalization_18 (Batc (None, 117, 128)          512       
_________________________________________________________________
dropout_18 (Dropout)         (None, 117, 128)          0         
_________________________________________________________________
time_distributed_6 (TimeDist (None, 117, 1)            129       
=================================================================
Total params: 1,056,721
Trainable params: 1,055,817
Non-trainable params: 904
_________________________________________________________________

--It seems that you can apply the fully connected layer to the time series by using TimeDistributed. --The fully connected layer of the activation function sigmoid is set in the final layer so that the probability is output.

X = TimeDistributed(Dense(1, activation='sigmoid'))(X)

--CuDNNL STM was used to prioritize speed ――I changed it because the progress was slow when I trained with normal LSTM. --CuDNNLSTM did not work on Colab when using Tensorflow ver2.0 series --Is it possible to use it by importing from tf.compat.v1.keras.layers? --This time, I tried it with ver 1.15.0 to save time.

Learning results

――We proceeded with the learning under the following conditions

detector = model(train_data_shape)
optimizer = Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, decay=0.01)
detector.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=["accuracy"])
history = detector.fit(X_train, y_train, batch_size=10,
             epochs=500, verbose=1, validation_data=(X_validation, y_validation))

――Learning proceeded in about 3s per epoch. High speed instead of CuDNNLSTM effect

Epoch 1/500
1050/1050 [==============================] - 5s 5ms/step - loss: 0.6187 - acc: 0.8056 - val_loss: 14.2785 - val_acc: 0.0648
Epoch 2/500
1050/1050 [==============================] - 3s 3ms/step - loss: 0.5623 - acc: 0.8926 - val_loss: 14.1574 - val_acc: 0.0733

――It is a transition of learning. It seemed that I was able to learn enough around 200 epoch

――The correct answer rate was high even in the TEST data.

detector.evaluate(X_test, y_test)
150/150 [==============================] - 0s 873us/step
[0.018092377881209057, 0.9983475764592489]

--It seemed that the prediction was almost accurate when compared with the correct label of the TEST data (blue: correct answer orange: prediction). ――It's too predictable and something is wrong

in conclusion

――I deepened my understanding of the flow from data generation to learning. ――It became a simple model that only detects voice, but it was a learning experience.

--The amount and variation of training data was insufficient ――Since there is no variation in utterance data, it seems that it will react to other words. --Maybe it's just detecting the part you're synthesizing

――In the future, I think it would be good if we could improve the model and data for learning, and use the results to create apps.

Thank you very much. Have a nice year this year as well.

reference

Recommended Posts

I tried to recognize the wake word
I tried to move the ball
I tried to estimate the interval.
I tried to summarize the umask command
I tried to summarize the graphical modeling.
I tried to estimate the pi stochastically
I tried to touch the COTOHA API
I tried to debug.
I tried to paste
I tried web scraping to analyze the lyrics.
I tried to optimize while drying the laundry
I tried to save the data with discord
I tried to touch the API of ebay
I tried to correct the keystone of the image
Qiita Job I tried to analyze the job offer
LeetCode I tried to summarize the simple ones
I tried to implement the traveling salesman problem
I tried to predict the price of ETF
I tried to vectorize the lyrics of Hinatazaka46!
I tried to graph the packages installed in Python
I tried to detect the iris from the camera image
I tried to summarize the basic form of GPLVM
I tried to touch the CSV file with Python
I tried to predict the J-League match (data analysis)
I tried to organize SVM.
I tried to solve the soma cube with python
I tried to implement PCANet
I tried to approximate the sin function using chainer
I tried the changefinder library!
I tried to put pytest into the actual battle
[Python] I tried to graph the top 10 eyeshadow rankings
I tried to reintroduce Linux
I tried to visualize the spacha information of VTuber
I tried to introduce Pylint
I tried to erase the negative part of Meros
I tried to solve the problem with Python Vol.1
I tried to summarize SparseMatrix
I tried to simulate the dollar cost averaging method
I tried to redo the non-negative matrix factorization (NMF)
I tried to touch jupyter
I tried to implement StarGAN (1)
I tried to identify the language using CNN + Melspectogram
I tried to notify the honeypot report on LINE
I tried to complement the knowledge graph using OpenKE
I tried to classify the voices of voice actors
I tried to compress the image using machine learning
I tried to summarize the string operations of Python
I tried to put out the frequent word ranking of LINE talk with Python
I tried to find the entropy of the image with python
I tried to find out the outline about Big Gorilla
I tried to introduce the block diagram generation tool blockdiag
I tried porting the code written for TensorFlow to Theano
[Horse Racing] I tried to quantify the strength of racehorses
I tried to simulate how the infection spreads with Python
I tried to analyze the whole novel "Weathering with You" ☔️
[First COTOHA API] I tried to summarize the old story
I tried to get the location information of Odakyu Bus
I tried to find the average of the sequence with TensorFlow
I tried to notify the train delay information with LINE Notify
I tried to simulate ad optimization using the bandit algorithm.
I tried to summarize the code often used in Pandas