proj

Mis-pronunciation Detection based on Phoneme Recognition
A Mis-pronunciation Detection system, with word-level aligned phonemes predictions.
Mu Yang
Audio Samples
Mis-pronunciation Detection based on Phoneme Recognition
Synthing: A WaveNet-based Singing Voice Synthisizer
Final project for USC course EE599: Deep Learning Lab for Speech Processing - a WaveNet-based singing voice synthesizer. This is a partial implementation of the paper A Neural Parametric Singing Synthesizer Modeling Timbre and Expression from Natural Songs.
Mu Yang, James Bunning, Shiyu Mou, Sharada Murali, Yixin Yang
PDF Code Dataset Audio Samples
Synthing: A WaveNet-based Singing Voice Synthisizer
Collection and Classification of Lyrics
Web crawler of lyrics and corresponding music genre. Multiple baseline classifiers, such as Naive Bayes, SVM and Neural Approach(LSTM) are applied to identify the genre of a song by analyzing its lyrics.
Mu Yang, Tao Chen, Chang Su, Zhe Yang
PDF Code
Collection and Classification of Lyrics
Digital Room Correction using Parallel Second-order Filter-based Equalizer
A Parallel second-order-based equalizer for Room Impulse Response Calibration.
Mu Yang
PDF Code Audio Samples
Digital Room Correction using Parallel Second-order Filter-based Equalizer
Faster-RCNN for Pedestrian Detection in Videos
Train and deploy a Faster-RCNN framework to perform pedestrain detection in videos.
Mu Yang
Faster-RCNN for Pedestrian Detection in Videos