Filters








1,815 Hits in 5.2 sec

Attentive Neural Architecture Incorporating Song Features For Music Recommendation [article]

Noveen Sachdeva, Kartik Gupta, Vikram Pudi
2018 pre-print
In this direction, we propose a novel attentive neural architecture which in addition to the sequence of items selected by the user, uses the features of these items to better learn the user short-term  ...  Attentive neural networks have been exploiting the sequence in which the items were selected by the user to model the implicit short-term interests of the user for the task of next item prediction, however  ...  of the two individual unidirectional hidden states: Figure 1 : 1 Attentive Neural Network Architecture for Next Song PredictionBoth the attention layers output a context vector which is a weighted sum  ... 
doi:10.1145/3240323.3240397 arXiv:1811.08203v1 fatcat:weuaohgna5estklzklrjfrs7sa

Multimodal Fusion Based Attentive Networks for Sequential Music Recommendation [article]

Kunal Vaswani, Yudhik Agrawal, Vinoo Alluri
2021 arXiv   pre-print
Modern methods leveraging the listening histories of users for session-based song recommendations have overlooked the significance of features extracted from lyrics and acoustic content.  ...  In this paper, we propose a novel deep learning approach by refining Attentive Neural Networks using representations derived via a Transformer model for lyrics and Variational Autoencoder for acoustic  ...  Overview of our proposed music recommendations architecture (ANN-Word2Vec + Acoustic + Lyrics).  ... 
arXiv:2110.01001v1 fatcat:mc3e4cn6rjfytly4r6lqgk2klm

Deep Learning in Music Recommendation Systems

Markus Schedl
2019 Frontiers in Applied Mathematics and Statistics  
Deep neural networks are used in this domain particularly for extracting latent factors of music items from audio signals or metadata and for learning sequential patterns of music items (tracks or artists  ...  music recommendation).  ...  propose an attentive neural network (ANN) architecture for next song prediction [27] . They use one-hot encoded representations of songs and of tags preceding the song to be predicted.  ... 
doi:10.3389/fams.2019.00044 fatcat:vvosxlygrravloyrj3qubflnoe

Music Emotion Recognition Model Using Gated Recurrent Unit Networks and Multi-Feature Extraction

Nana Niu, Liping Zhang
2022 Mobile Information Systems  
The deep learning framework for music recommendation is still very limited when it comes to accurately identifying the emotional type of music and recommending it to users.  ...  It can meet users' needs for music recognition in a variety of settings.  ...  . 10 Mobile Information Systems Model Average accuracy (%) 1st song + BiGRU + self-attention 61.8 Top 3 songs + BiGRU + self-attention 65.7 Top 5 songs + BiGRU + self-attention 67.2 Top 7 songs + BiGRU  ... 
doi:10.1155/2022/5732687 fatcat:jjae3ilyozbddhpcj3fxni672y

Learning Recommendation Algorithm Based on Improved BP Neural Network in Music Marketing Strategy

Lei Li, Suneet Kumar Gupta
2021 Computational Intelligence and Neuroscience  
Convolutional neural networks are used to extract the high-level semantic features of songs, and then the high-level semantic features of songs extracted from the previous layer are reformed into a session  ...  To address the sparsity of behavioral data in digital music marketing, which leads to inadequate mining of user music preference features, a metric ranking learning recommendation algorithm with fused  ...  Music Recommendation Algorithms Incorporating Song Content.  ... 
doi:10.1155/2021/2073881 pmid:34887911 pmcid:PMC8651361 fatcat:iqtezfugjrhtnd3rsuurrbh5hi

Lukthung Classification Using Neural Networks on Lyrics and Audios [article]

Kawisorn Kamtue, Kasina Euchukanonchai, Dittaya Wanvarie, Naruemon Pratanwanich
2019 arXiv   pre-print
Being able to automatically tag genres will benefit music streaming service providers such as JOOX, Apple Music, and Spotify for their content-based recommendation.  ...  However, most studies on music classification have been done on western songs which differ from Thai songs.  ...  Therefore, for the purpose of personalized music recommendation in the Thai music industry, identifying Lukthung songs in hundreds of thousands of songs can reduce the chance of mistakenly recommending  ... 
arXiv:1908.08769v2 fatcat:q2nergkedvbd5ajfxbwkvryma4

Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation [article]

Tingle Li, Jiawei Chen, Haowen Hou, Ming Li
2020 arXiv   pre-print
In this paper, we propose a Sliced Attention-based neural network (Sams-Net) in the spectrogram domain for the music source separation task.  ...  It enables spectral feature interactions with multi-head attention mechanism, achieves easier parallel computing and has a larger receptive field compared with LSTMs and CNNs respectively.  ...  Conclusions In this paper, we propose a sliced attention-based neural network for music source separation, named Sams-Net.  ... 
arXiv:1909.05746v4 fatcat:l55l4lclajfmrejnqsr6f5sw4u

Deep Content-User Embedding Model for Music Recommendation [article]

Jongpil Lee, Kyungyun Lee, Jiyoung Park, Jangyeon Park, Juhan Nam
2018 arXiv   pre-print
We evaluate the model on music recommendation and music auto-tagging tasks. The results show that the proposed model significantly outperforms the previous work.  ...  In this work, we propose deep content-user embedding model, a simple and intuitive architecture that combines the user-item interaction and music audio content.  ...  INTRODUCTION Music recommendation has gained more attention in recent years as accessibility to music has dramatically increased by music streaming services and recommending songs that satisfy users' taste  ... 
arXiv:1807.06786v1 fatcat:djezbsohvjfn3b5fta2qyt3ywy

Matching User with Item Set: Collaborative Bundle Recommendation with Deep Attention Network

Liang Chen, Yang Liu, Xiangnan He, Lianli Gao, Zibin Zheng
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
We contribute a neural network solution named DAM, short for Deep Attentive Multi-Task model, which is featured with two special designs: 1) We design a factorized attention network to aggregate the item  ...  However, in many real-world scenarios, the platform needs to show users a set of items, e.g., the marketing strategy that offers multiple items for sale as one bundle.In this work, we consider recommending  ...  Introducing Innovative and Entrepreneurial Teams (2017ZT07X355) and the Fundamental Research Funds for the Central Universities under Grant (17lgpy117).  ... 
doi:10.24963/ijcai.2019/290 dblp:conf/ijcai/ChenL0GZ19 fatcat:nal6bfu6fnej5kar5ra6d2qg6m

Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works

Ayush Singhal, Pradeep Sinha, Rakesh Pant
2017 International Journal of Computer Applications  
for recommendation.  ...  With the exponential increase in the amount of digital information over the internet, online shops, online music, video and image libraries, search engines and recommendation system have become the most  ...  The model handles both the status users and item features as well as the dynamic reading interests of the users using attention based recurrent neural networks.  ... 
doi:10.5120/ijca2017916055 fatcat:m6icpquumbgczhrdnya7x35of4

MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms [article]

Kai Middlebrook, Shyam Sudhakaran, David Guy Brizan
2021 arXiv   pre-print
The backend dynamically recalibrates multi-scale and level features extracted from the frontend by incorporating self-attention.  ...  We present MuSLCAT, or Multi-scale and Multi-level Convolutional Attention Transformer, a novel architecture for learning robust representations of complex music tags directly from raw waveform recordings  ...  Deep neural networks for discriminative music tasks Recent research shows feature learning approaches that use a deep neural network (DNN) outperform traditional handcrafted feature modeling approaches  ... 
arXiv:2104.02309v1 fatcat:rldn5djakng6bohslqzujhhpu4

Evaluation of CNN-based Automatic Music Tagging Models [article]

Minz Won, Andres Ferraro, Dmitry Bogdanov, Xavier Serra
2020 arXiv   pre-print
Music information retrieval (MIR) researchers proposed various architecture designs, mainly based on convolutional neural networks (CNNs), that achieve state-of-the-art results in this multi-label binary  ...  To facilitate further research, in this paper we conduct a consistent evaluation of different music tagging models on three datasets (MagnaTagATune, Million Song Dataset, and MTG-Jamendo) and provide reference  ...  Typically these tags carry useful semantic music information that can later be used for other applications such as music recommendation or music retrieval.  ... 
arXiv:2006.00751v1 fatcat:w6wn445kybc3zhouoq52gcx2ti

Evaluation of CNN-based automatic music tagging models

Minz Won, Andres Ferraro, Dmitry Bogdanov, Xavier Serra
2020 Zenodo  
Music information retrieval (MIR) researchers proposed various architecture designs, mainly based on convolutional neural networks (CNNs), that achieve state-of-the-art results in this multi-label binary  ...  To facilitate further research, in this paper we conduct a consistent evaluation of different music tagging models on three datasets (MagnaTagATune, Million Song Dataset, and MTGJamendo) and provide reference  ...  Typically these tags carry useful semantic music information that can later be used for other applications such as music recommendation or music retrieval.  ... 
doi:10.5281/zenodo.3898838 fatcat:6z6gbr7t65ca5fuhkkj446atty

Neural Encoding of Songs is Modulated by Their Enjoyment [article]

Gulshan Sharma, Pankaj Pandey, Ramanathan Subramanian, Krishna. P. Miyapuram, Abhinav Dhall
2022 arXiv   pre-print
We examine user and song identification from neural (EEG) signals. Owing to perceptual subjectivity in human-media interaction, music identification from brain signals is a challenging task.  ...  We demonstrate that subjective differences in music perception aid user identification, but hinder song identification.  ...  ACKNOWLEDGEMENTS We thank Science and Engineering Research Board (SERB) and PlayPower Labs for supporting the Prime Minister's Research Fellowship (PMRF) awarded to Pankaj Pandey and FICCI for facilitating  ... 
arXiv:2208.06679v1 fatcat:ni4t7qghwjdklkwwkzzamkpose

Deep Learning for Emotion Recognition in Affective Virtual Reality and Music Applications

2019 International journal of recent technology and engineering  
Rather than applying music genres or lyrics into machine learning algorithm to MER, higher representation of music information, acoustic features are used.  ...  In conjunction with the four classes classification problem, an available dataset named AMG1608 is feed into a training model built from deep neural network.  ...  The objective is to build a music emotion recommender system using deep architectures of artificial neural networks to make song recommendations to humans.  ... 
doi:10.35940/ijrte.b1030.0782s219 fatcat:3utdzdkkxbhebnimqsl7na7auq
« Previous Showing results 1 — 15 out of 1,815 results