基于深度学习的婴儿啼哭识别项目详解

一、项目背景

婴儿啼哭声是婴儿沟通需求的重要信号，对于父母和护理者而言至关重要。本项目基于PaddleSpeech框架，致力于构建婴儿啼哭识别系统，通过深度学习将啼哭声翻译成成人语言，帮助理解婴儿的需求和状态。

1.1 项目背景

婴儿啼哭声是一种生物报警器，传递婴儿的生理和心理需求。有效地识别啼哭声有助于提高婴儿护理的效率和质量。

1.2 数据说明

项目使用六类人工添加噪声的哭声作为训练数据集，分别代表不同的婴儿需求，如苏醒、换尿布、要抱抱、饥饿、困乏、不舒服。噪声数据来自Noisex-92标准数据库。

二、PaddleSpeech环境准备

安装PaddleSpeech和PaddleAudio，确保环境准备就绪。

!python -m pip install -q -U pip --user
!pip install paddlespeech paddleaudio -U -q

三、数据预处理

3.1 数据解压缩

解压缩训练数据集，获取音频文件。

!unzip -qoa data/data41960/dddd.zip

3.2 查看声音文件

通过可视化展示音频波形，了解样本数据的特征。

from paddleaudio import load
data, sr = load(file='train/awake/awake_0.wav', mono=True, dtype='float32')  
print('wav shape: {}'.format(data.shape))
print('sample rate: {}'.format(sr))
plt.figure()
plt.plot(data)
plt.show()

3.3 音频文件长度处理

统一音频文件长度，确保训练数据格式一致。

# 音频信息查看
import soundfile as sf
import numpy as np
import librosadata, samplerate = sf.read('hungry_0.wav')
channels = len(data.shape)
length_s = len(data) / float(samplerate)
format_rate = 16000
print(f"channels: {channels}")
print(f"length_s: {length_s}")
print(f"samplerate: {samplerate}")

四、自定义数据集与模型训练

4.1 自定义数据集

创建自定义数据集类，包含六类婴儿需求的音频文件。

class CustomDataset(AudioClassificationDataset):# List all the class labelslabel_list = ['awake','diaper','hug','hungry','sleepy','uncomfortable']train_data_dir = './train/'def __init__(self, **kwargs):files, labels = self._get_data()super(CustomDataset, self).__init__(files=files, labels=labels, feat_type='raw', **kwargs)# 返回音频文件、label值def _get_data(self):'''This method offer information of wave files and labels.'''files = []labels = []for i in range(len(self.label_list)):single_class_path = os.path.join(self.train_data_dir, self.label_list[i])for sound in os.listdir(single_class_path):if 'wav' in sound:sound = os.path.join(single_class_path, sound)files.append(sound)labels.append(i)return files, labels

4.2 模型训练

选取预训练模型作为特征提取器，构建分类模型进行模型训练。

# 选取cnn14作为 backbone，用于提取音频的特征
from paddlespeech.cls.models import cnn14
backbone = cnn14(pretrained=True, extract_embedding=True)# 构建分类模型
class SoundClassifier(nn.Layer):def __init__(self, backbone, num_class, dropout=0.1):super().__init__()self.backbone = backboneself.dropout = nn.Dropout(dropout)self.fc = nn.Linear(self.backbone.emb_size, num_class)def forward(self, x):x = x.unsqueeze(1)x = self.backbone(x)x = self.dropout(x)logits = self.fc(x)return logitsmodel = SoundClassifier(backbone, num_class=len(train_ds.label_list))

4.3 模型训练

定义优化器和损失函数，进行模型训练。

# 定义优化器和 Loss
optimizer = paddle.optimizer.Adam(learning_rate=1e-4, parameters=model.parameters())
criterion = paddle.nn.loss.CrossEntropyLoss()# 模型训练
epochs = 20
steps_per_epoch = len(train_loader)
log_freq = 10
eval_freq = 10for epoch in range(1, epochs + 1):model.train()avg_loss = 0num_corrects = 0num_samples = 0for batch_idx, batch in enumerate(train_loader):waveforms, labels = batchfeats = feature_extractor(waveforms)feats = paddle.transpose(feats, [0, 2, 1])  logits = model(feats)loss = criterion(logits, labels)loss.backward()optimizer.step()if isinstance(optimizer._learning_rate, paddle.optimizer.lr.LRScheduler):optimizer._learning_rate.step()optimizer.clear_grad()# 计算损失avg_loss += loss.numpy()[0]# 计算指标preds = paddle.argmax(logits, axis=1)num_corrects += (preds == labels).numpy().sum()num_samples += feats.shape[0]if (batch_idx + 1) % log_freq == 0:lr = optimizer.get_lr()avg_loss /= log_freqavg_acc = num_corrects / num_samplesprint_msg = 'Epoch={}/{}, Step={}/{}'.format(epoch, epochs, batch_idx + 1, steps_per_epoch)print_msg += ' loss={:.4f}'.format(avg_loss)print_msg += ' acc={:.4f}'.format(avg_acc)print_msg += ' lr={:.6f}'.format(lr)logger.train(print_msg)avg_loss = 0num_corrects = 0num_samples = 0

五、模型测试

通过模型对测试音频进行推理，输出对应的婴儿需求概率。

# 模型测试
top_k = 3
wav_file = 'test/test_0.wav'
n_fft = 1024
win_length = 1024
hop_length = 320
f_min = 50.0
f_max = 16000.0waveform, sr = load(wav_file, sr=sr)
feature_extractor = LogMelSpectrogram(sr=sr, n_fft=n_fft, hop_length=hop_length, win_length=win_length, window='hann', f_min=f_min, f_max=f_max, n_mels=64)
feats = feature_extractor(paddle.to_tensor(paddle.to_tensor(waveform).unsqueeze(0)))
feats = paddle.transpose(feats, [0, 2, 1])logits = model(feats)
probs = nn.functional.softmax(logits, axis=1).numpy()sorted_indices = probs[0].argsort()msg = f'[{wav_file}]\n'
for idx in sorted_indices[-1:-top_k-1:-1]:msg += f'{train_ds.label_list[idx]}: {probs[0][idx]:.5f}\n'
print(msg)

六、注意事项

1. 自定义数据集格式参考文档；
2. 统一音频尺寸，确保音频长度和采样频率一致；
3. 可学习PaddleSpeech课程。