7 skills found
mever-team / AusilAuthors official Tensorflow implementation of the "Audio-based Near-Duplicate Video Retrieval with Audio Similarity Learning" [ICPR 2020]
SonamSangpoLama / Music Genre ClassificationMusic genres is the taste, style and relax giving flow of a music. The genre of music refers to multiple types and categorization of music. The different types of famous music genre that we widely known are rock, jazz, reggae, classical, folk, blues, R & B, metal, dubstep, techno, country music, electro and pop. The key success of music in music industry is the genres of classified music that becomes a significant part of communicating music that provides bonding with relatively to human and masses of people. In contrast, the genre that falls under top-level style of rock are punk, indie, shoegaze, AOR and metal. They are basically subgenre of a music classification and it is important describing music to other people. In practical life, music is often used for multiple purposes due to physiological and social effects. Companies like Spotify, Soundcloud, Apple Music, Wynk & products like Shazam use music classification to provide their customers different flavour of music by recommending music they prefer to listen. we use python libraries such as Librosa and PyAudio library for audio processing in Python. We apply and use GTZAN dataset that is composed of 1000 audio tracks each 30-second-long representing 10 genres with 22050Hz mono audio file of 16bit in .au format for dataset. The functionality and working of music genre classification determine the help of Machine Learning algorithms. The algorithm such as KNN and artificial neural network (ANN) analyses and find out the similar similarity of genre features of music and classify it.
jonrosner / AudioSimilarityThesis and code for my Master's Thesis in Informatics titled "Deep Learning for Determining Audio Similarity"
5W4PN1L / Audio Matching ToolThis project enhances audio similarity detection using machine learning and signal processing. By leveraging Python libraries like Librosa and Resemblyzer, it extracts voice embeddings and computes cosine similarity. Advanced techniques like MFCC and chroma features improve accuracy, even with noise variations.
reggiebain / Song Similarity ErdosBuilding a model for detecting song similarity using features derived from raw audio made for 2024 Erdos Institute Deep Learning course. Authored by Reggie Bain, Emelie Curl, Larsen Linov, Tong Shan, and Glenn Young
ddm06 / Classification Of Musical Genres And Music RetrievalDuring the project for the DIGITAL SIGNAL IMAGE MANAGEMENT course I learned how to manage and process audio and image files. The aim of the project was the classification, through machine learning and deep learning models, of musical genres by extracting specific audio features from the "gtzan dataset" dataset files with which to train the models (SVM, Linear Regression, Decision tree , Random Forest, Neural Network). Mel spectograms were also extracted to train convolutional neural network models. In addition, the extracted audio features have been used to develop a model of music retrieval which given an audio track in input produces as output 5 audio tracks recommended meiante the use of cousine similarity.
pranshu05 / Song2VecCompare musical similarity between two songs using audio signal processing and machine learning.
