Discover leonardltk/Speech-Enhancement-Using-Time-Domain-Loss Open

Stars
8
Rank 2,099,232 (Top 42 %)
Language
Python
Created over 4 years ago
Updated over 4 years ago

leonardltk

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

This is an adaptation of the paper "Two-Stage Deep Learning for Noisy-Reverberant Speech Enhancement". It uses Time Domain Reconstruction (TDR) as an additional loss function to make use of clean phase in the enhancement process. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6519714/

Shazam-An-Industrial-Strength-Audio-Search-Algorithm-

Detecting segments belonging to which song in database, and return Nil if does not exist in a database.

Python

Deep-Learning-Developer-Course-Projects

Jupyter Notebook

Deep-Convolutional-ResNet-Audio-Duplicate-Detector

A Deep CNN for short audio (~15 seconds) Duplicate Detector is trained in a siamese style fashion.

Python

RAGcipe

Use LLM + Advanced RAG to get desired #ROTD (recipe of the day)

Jupyter Notebook

AndroidAudioWaveViewer