mel-spectrogram 开源项目推荐（164 个）

BShakhovsky /PolyphonicPianoTranscription

Recurrent Neural Network for generating piano MIDI-files from audio (MP3, WAV, etc.)

Sharad24 /Neural-Voice-Cloning-with-Few-Samples

Implementation of Neural Voice Cloning with Few Samples Research Paper by Baidu

tiberiu44 /TTS-Cube

End-2-end speech synthesis with recurrent neural networks

Data-Science-kosta /Speech-Emotion-Classification-with-PyTorch

This repository contains PyTorch implementation of 4 different models for classification of emotions of the speech.

cwx-worst-one /WavTTS

WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling

spotify /realbook

用TensorFlow实现更简单的音频机器学习。

CVxTz /audio_classification

CNN 1D vs 2D audio classification

MycroftAI /sonopy

A simple audio feature extraction library

echocatzh /torch-mfcc

A librosa STFT/Fbank/mfcc feature extration written up in PyTorch using 1D Convolutions.

zzw922cn /LPC_for_TTS

Linear Prediction Coefficients estimation from mel-spectrogram implemented in Python based on Levinson-Durbin algorithm.

rednafi /urban-sound-classification

Urban sound source tagging from an aggregation of four second noisy audio clips via 1D and 2D CNN (Xception)

zafarrafii /Zaf-Python

Zafar的Python音频函数用于音频信号分析：STFT、逆STFT、mel滤波器组、mel频谱图、MFCC、CQT核、CQT频谱图、CQT色图、DCT、DST、MDCT、逆MDCT。

kbhujbal /SudarshanChakra-acoustic_uav_threat_detection_CNN

🔇 A production-grade deep learning system for real-time drone/UAV detection through acoustic signature analysis. Converts raw audio to Mel-Spectrograms and classifies using a custom CNN. Features auto-dataset ingestion, defense-optimized metrics (high recall), early stopping, model checkpointing, and a ready-to-use inference API.

zafarrafii /Zaf-Matlab

Zafar's Audio Functions in Matlab for audio signal analysis: STFT, inverse STFT, mel filterbank, mel spectrogram, MFCC, CQT kernel, CQT spectrogram, CQT chromagram, DCT, DST, MDCT, inverse MDCT.

skanderhamdi /attention_cnn_lstm_covid_mel_spectrogram

Attention-based Hybrid CNN-LSTM and Spectral Data Augmentation for COVID-19 Diagnosis from Cough Sound

ccmusic-database /pianos

This study converts piano recordings to mel spectrogram and classifies them by SOTA pre-trained neural network backbones in CV. Comparative experiments show that SqueezeNet achieves a best classification accuracy of 92.37%.|该项目将钢琴录音转为为mel频谱图，使用微调后的前沿计算机视觉领域预训练深度学习骨干网络对其进行分类，对比实验可知SqueezeNet作为最优网络正确率可达92.37%

lunashia /o-m_beatmap_trainer

Training pipeline for an osu!mania 7k next-event model, designed as the upstream predictor for audio-driven 7k map generation systems.

Friedrich-M /Audio-signal-classification-and-identification

Signal classification and recognition based on Mel spectrograms

ddman1101 /EDM-subgenre-classifier

Code for "Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features" arXiv:2110.08862, 2021.

yoyolicoris /wavenet-like-vocoder

Basic wavenet and fftnet vocoder model.