├── .gitignore ├── resources ├── PLP.PNG ├── summary.PNG ├── mel-banks.PNG ├── 39d_feature.PNG ├── mel_filters.jpg ├── output_13_0.png ├── output_14_0.png ├── output_18_0.png ├── output_19_0.png ├── output_27_1.png ├── output_29_0.png ├── output_30_0.png ├── output_34_0.png ├── output_41_0.png ├── output_46_0.png ├── output_49_0.png ├── output_56_0.png ├── output_58_0.png ├── OSR_us_000_0010_8k.wav └── speech_production_model.PNG └── README.md /.gitignore: -------------------------------------------------------------------------------- 1 | .ipynb_checkpoints 2 | -------------------------------------------------------------------------------- /resources/PLP.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/PLP.PNG -------------------------------------------------------------------------------- /resources/summary.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/summary.PNG -------------------------------------------------------------------------------- /resources/mel-banks.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/mel-banks.PNG -------------------------------------------------------------------------------- /resources/39d_feature.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/39d_feature.PNG -------------------------------------------------------------------------------- /resources/mel_filters.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/mel_filters.jpg -------------------------------------------------------------------------------- /resources/output_13_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_13_0.png -------------------------------------------------------------------------------- /resources/output_14_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_14_0.png -------------------------------------------------------------------------------- /resources/output_18_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_18_0.png -------------------------------------------------------------------------------- /resources/output_19_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_19_0.png -------------------------------------------------------------------------------- /resources/output_27_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_27_1.png -------------------------------------------------------------------------------- /resources/output_29_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_29_0.png -------------------------------------------------------------------------------- /resources/output_30_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_30_0.png -------------------------------------------------------------------------------- /resources/output_34_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_34_0.png -------------------------------------------------------------------------------- /resources/output_41_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_41_0.png -------------------------------------------------------------------------------- /resources/output_46_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_46_0.png -------------------------------------------------------------------------------- /resources/output_49_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_49_0.png -------------------------------------------------------------------------------- /resources/output_56_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_56_0.png -------------------------------------------------------------------------------- /resources/output_58_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/output_58_0.png -------------------------------------------------------------------------------- /resources/OSR_us_000_0010_8k.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/OSR_us_000_0010_8k.wav -------------------------------------------------------------------------------- /resources/speech_production_model.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Magic-Bubble/SpeechProcessForMachineLearning/HEAD/resources/speech_production_model.PNG -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # SpeechProcessForMachineLearning 2 | 3 | 用于机器学习的语音特征提取，包含FBank和MFCC等，原理讲解和step by step的实现 4 | 5 | 精华版博客链接：https://blog.csdn.net/Magical_Bubble/article/details/90295814 6 | 7 | 完整JupyterNotebook链接：https://github.com/Magic-Bubble/SpeechProcessForMachineLearning/blob/master/speech_process.ipynb --------------------------------------------------------------------------------