hadryan Goto Github PK

mtf-crnn

Inspired by the convolutional recurrent neural network(CRNN) and inception, we propose a multiscale time-frequency convolutional recurrent neural network (MTF-CRNN) for audio event detection. Our goal is to improve audio event detection performance and recognize target audio events that have different lengths and accompany the complex audio background. We exploit multi-groups of parallel and serial convolutional kernels to learn high-level shift invariant features from the time and frequency domains of acoustic samples. A two-layer bi-direction gated recurrent unit) based on the recurrent neural network is used to capture the temporal context from the extracted high-level features. The proposed method is evaluated on the DCASE2017 challenge dataset. Compared to other methods, the MTF-CRNN achieves one of the best test performances for a single model without pre-training and without using a multi-model ensemble approach.

mtg-jamendo-dataset

Metadata, scripts and baselines for the MTG-Jamendo dataset

mubert-text-to-music

A simple notebook demonstrating prompt-based music generation via Mubert API

multi-level-form-backbone.js

Backbone.js related codes

multi-model-approach-for-speak-and-text-image-association-prediction

Our task is to Recognize whether an image of a hand-written digit and a recording of a spoken digit refer to the same or different number. We have two input data written number image and number spoken sound MFCC features and one output consist of boolean array state that the respective sound and image matches or not. We choose multi model approach using LSTM for audio features and CNN for image data. The output of both model concatenated at the end and binary loss function applied.

multi-task-nlp

multi_task_NLP is a utility toolkit enabling NLP developers to easily train and infer a single model for multiple tasks.

multiavatar-php

Multiavatar Generator in PHP

multidistance-recommendation-calculation-

Euclidean Distance Method + Manhatan Distance Method + Minkowski Distance Method + Chebychef Distance Method + Canbera Distance Method + Bray Curtis Distance Method + Kullback Leibler Distance Method + Jensen Shannon Distance Method

multilingual-glm

The multilingual variant of GLM, a general language model trained with autoregressive blank infilling objective

multimodal-music-recommender

Extracting visual features from "Music Videos" for Video Recommender

multimodal-speech-emotion

TensorFlow implementation of "Multimodal Speech Emotion Recognition using Audio and Text," IEEE SLT-18

multimodal_movie_analysis

A Python Library for Multimodal Analysis of Movies and Content-based Movie Recommendation

multimodalanalysis

Python examples for the course "Multimodal Information Processing & Analysis" of the MSc in Data Science in NCSR Demokritos

multimodalanalysis_speakerdiarization

The project tries to solve a speaker diarization problem using audio features, face recognition and video feature extraction from face image, mouth tracking.

multiprocess

🚀Easy to make the common PHP/Python/js...script change daemon and multi-process execution

multitaskobjectstates

Code for the paper "Multi-Task Learning of Object State Changes from Uncurated Videos"

multiviewadapter

Easily create complex recyclerview adapters in android

mumbl

A JavaScript library that abstracts audio-playing functionality of HTML5, Songbird, and SoundManager 2 for use in music playlists

mumble_display

simple javascript display for mumble, using D3.js (WIP)

mure

music recommender system

mus-recom

musan_investigation_cnn_rnn

Evaluation of the classification performance (Speech, Music, and Noise) of 1D (WaveNet) and 2D (MobileNet) CNN and RNN (GRU) on the MUSAN corpus.

muse

will recommend you songs based on the vocals/mood/vibe

musescore-downloader

Download sheet music (MSCZ, PDF, MusicXML, MIDI, MP3, download individual parts as PDF) from musescore.com for free, no login or Musescore Pro required | 免登录、免 Musescore Pro，免费下载 musescore.com 上的曲谱 | Installation: https://msdl.librescore.org/install.user.js

music

Music player based on Auro

music-1

electron跨平台音乐播放器；可搜网易云、QQ音乐、虾米音乐；支持QQ、微博、Github登录，云歌单; 支持一键导入音乐平台歌单

music-2

Emotion Based music player

music-album-recommendation-system

music-alignment-detection

Automatic alignment detection of a song’s music and lyric emotions

music-artist-classification-crnn

Supplementary material for IJCNN paper "Musical Artist Classification with Convolutoinal Recurrent Neural Networks"