README.md

Speech Algorithms

The implementation of various speech algorithms can be downloaded individually through DownGit.

Content

Speech singal processing

Title	Code
Generate Speech Samples with noisy/echo/reverbed/howling	Code
Resample Speech Signal at Arbitrary Sample Rate	Code
Embedding and Extracting Audio Digital Watermarkings	Code
Voice Speed and Pitch Changes	Code
Enframe, Windowing and DFT	Code
Audio Aligment with Cross-correlation	Code
Music Recognition System Based on Audio Fingerprinting	Code
Goertzel Algorithm	Code
Generate the Sound of Rain	Code

Speech front-end algorithms

Title	Code
Speech Enhancement Using Spectral Subtraction	Code
Speech Speration Based on TF Mask	Code
Introduction of Adaptive Filter Echo Cancellation	Code
Generate VAD Labels Using AMR Codec	Code
Introduction of WebRTC VAD	Code
Acoustic Echo Cancellation Algorithm Based on Kalman Filter	Code
Introduction of WebRTC ANR	Code
Introduction of WebRTC AGC	Code
Introduction of WebRTC AEC	Code
Single Channel Speech Enhancement Using DNN	Code
Data Augmentations for Speech Enhancement	Code
How to Generate Howling Samples	Code
Transient Noise Suppression	Code
Endpoint Detection Using LSTM	Code

Microphone array algorithms

Title	Code
CGMM-MVDR	Code
Sound Source Localization Based on TDOA	Code

Speech Pattern Recognition

Title	Code
Speech Commands Recognition Using CNN	Code
Speaker Gender Identification	Code
Environmental Sound Classification Using XGBoost	Code
CTC Prefix Beam Search	Code

Speech Codec

Title	Code
AI Speech Codec	Code
G.711 Speech Codec	Code

Speech Metrics

Title	Code
Speech Quality Metrics	Code
Speech Intelligibility Metrics	Code
Speech Similarity Evaluation	Code