YichiHuang
CS graduate student. Research interests include speaker recognition and NLP.
Peking University Shenzhen Graduate SchoolShenzhen, Guangdong Province
Pinned Repositories
AudioMLProject1
Voice Activity Detection: In this first assignment, we will create a dataset that simulates speech in every-day scenarios. We train a classifier on this dataset for distinguishing voiced from non-voiced sections, a task called voice activity detection, VAD for short. This, of course, requires a ground truth in terms of VAD annotations.
AudioMLProject2
Speaker Detection: We have one target speaker whom we want to detect. The set of impostors is open, i.e., we have no prior information on the test speakers. An important part of the speaker detection pipeline is voice activity detection to filter out segments of the signal that do not contain speech.
AudioMLProject3
Emotion recognition of Speaker's Speech Data. Employ speaker detection classifiers for emotion recognition, a multiclass classification problem. Emotion Classes: Happy, Sad, Neutral, Relaxed and Angry
DeepXi
Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2. For speech enhancement and robust ASR.
karry
I want to develop a voice-control product named "karry".
models
Models and examples built with TensorFlow
MTDSR2015
A mandarin corpus for text-dependent speaker recognition.
publications
Includes all the papers and other publications of me.
speech_rec_py
Speech recognition application developed by Python. Use Eclipse with Pydev, Anancoda and PyQt. Call baidu yuyin API. Machine learning course demo.
Standford-machine-learning-exercise
Coursera machine learning course matlab exercise.
YichiHuang's Repositories
YichiHuang/MTDSR2015
A mandarin corpus for text-dependent speaker recognition.
YichiHuang/speech_rec_py
Speech recognition application developed by Python. Use Eclipse with Pydev, Anancoda and PyQt. Call baidu yuyin API. Machine learning course demo.
YichiHuang/models
Models and examples built with TensorFlow
YichiHuang/AudioMLProject1
Voice Activity Detection: In this first assignment, we will create a dataset that simulates speech in every-day scenarios. We train a classifier on this dataset for distinguishing voiced from non-voiced sections, a task called voice activity detection, VAD for short. This, of course, requires a ground truth in terms of VAD annotations.
YichiHuang/AudioMLProject2
Speaker Detection: We have one target speaker whom we want to detect. The set of impostors is open, i.e., we have no prior information on the test speakers. An important part of the speaker detection pipeline is voice activity detection to filter out segments of the signal that do not contain speech.
YichiHuang/AudioMLProject3
Emotion recognition of Speaker's Speech Data. Employ speaker detection classifiers for emotion recognition, a multiclass classification problem. Emotion Classes: Happy, Sad, Neutral, Relaxed and Angry
YichiHuang/DeepXi
Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2. For speech enhancement and robust ASR.
YichiHuang/karry
I want to develop a voice-control product named "karry".
YichiHuang/publications
Includes all the papers and other publications of me.
YichiHuang/Standford-machine-learning-exercise
Coursera machine learning course matlab exercise.
YichiHuang/yichihuang.github.io
My old github blog. New blog has changed to ychuang.github.io.