segment-modeler-DE

a neural network-based approach for the prediction of German phonemes in audio files using both spectrogram data and Mel-frequency cepstral coefficients (MFCCs)

Sources:

• http://www.kiranjose.in/blogs/getting-started-with-tensorflow-speech-recognition-api-and-object-detection-api/

• https://www.tensorflow.org/versions/master/tutorials/audio_recognition

• https://github.com/llSourcell/tensorflow_speech_recognition_demo

• https://www.isca-speech.org/archive/interspeech_2015/papers/i15_1478.pdf

• https://arxiv.org/pdf/1303.5778.pdf

• http://www.cs.toronto.edu/~graves/icml_2006.pdf

Fun reading:

• https://medium.com/@ageitgey/machine-learning-is-fun-part-6-how-to-do-speech-recognition-with-deep-learning-28293c162f7a