Design of Audio Signal Processing System Based on Machine Learning
Aiming at the intelligent demand in audio signal processing,an audio signal processing system based on machine learning is proposed.The system adopts three-tier architecture,which realizes audio feature extraction,machine learning model training and audio processing strategy optimization respectively.The speech recognition experiment is carried out on TIMIT speech data set,and the results show that the designed system has achieved good performance in phoneme error rate and real-time performance,and has certain noise robustness.
audio signal processingmachine learningfeature extraction
NETL
NSTL
万方数据
