Transformer-Based Seq2Seq Model for Chord Progression Generation

被引:4
|
作者
Li, Shuyu [1 ]
Sung, Yunsick [2 ]
机构
[1] Dongguk Univ Seoul, Grad Sch, Dept Multimedia Engn, Seoul 04620, South Korea
[2] Dongguk Univ Seoul, Dept Multimedia Engn, Seoul 04620, South Korea
基金
新加坡国家研究基金会;
关键词
chord progression generation; transformer; sequence-to-sequence; pre-training;
D O I
10.3390/math11051111
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Machine learning is widely used in various practical applications with deep learning models demonstrating advantages in handling huge data. Treating music as a special language and using deep learning models to accomplish melody recognition, music generation, and music analysis has proven feasible. In certain music-related deep learning research, recurrent neural networks have been replaced with transformers. This has achieved significant results. In traditional approaches with recurrent neural networks, input sequences are limited in length. This paper proposes a method to generate chord progressions for melodies using a transformer-based sequence-to-sequence model, which is divided into a pre-trained encoder and decoder. A pre-trained encoder extracts contextual information from melodies, whereas a decoder uses this information to produce chords asynchronously and finally outputs chord progressions. The proposed method addresses length limitation issues while considering the harmony between chord progressions and melodies. Chord progressions can be generated for melodies in practical music composition applications. Evaluation experiments are conducted using the proposed method and three baseline models. The baseline models included the bidirectional long short-term memory (BLSTM), bidirectional encoder representation from transformers (BERT), and generative pre-trained transformer (GPT2). The proposed method outperformed the baseline models in Hits@k (k = 1) by 25.89, 1.54, and 2.13 %, respectively.
引用
收藏
页数:14
相关论文
共 50 条
  • [21] Survival Seq2Seq: A Survival Model based on Sequence to Sequence Architecture
    Pourjafari, Ebrahim
    Ziaei, Navid
    Rezaei, Mohammad R.
    Sameizadeh, Amir
    Shafiee, Mohammad
    Alavinia, Mohammad
    Abolghasemian, Mansour
    Sajadi, Nick
    Proceedings of Machine Learning Research, 2022, 182 : 79 - 100
  • [22] Survival Seq2Seq: A Survival Model based on Sequence to Sequence Architecture
    Pourjafari, Ebrahim
    Ziaei, Navid
    Rezaei, Mohammad R.
    Sameizadeh, Amir
    Shafiee, Mohammad
    Alavinia, Mohammad
    Abolghasemian, Mansour
    Sajadi, Nick
    MACHINE LEARNING FOR HEALTHCARE CONFERENCE, VOL 182, 2022, 182 : 79 - 100
  • [23] Sentence-Chain Based Seq2seq Model for Corpus Expansion
    Chung, Euisok
    Park, Jeon Gue
    ETRI JOURNAL, 2017, 39 (04) : 455 - 466
  • [24] Network Penetration Intrusion Prediction Based on Attention Seq2seq Model
    Yu, Tianxiang
    Xin, Yang
    Zhu, Hongliang
    Tang, Qifeng
    Chen, Yuling
    SECURITY AND COMMUNICATION NETWORKS, 2022, 2022
  • [25] Residual Seq2Seq model for Building energy management
    Kim, Marie
    Kim, Nae-soo
    Song, YuJin
    Pyo, Cheol Sig
    2019 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC): ICT CONVERGENCE LEADING THE AUTONOMOUS FUTURE, 2019, : 1126 - 1128
  • [26] Seq2Seq dynamic planning network for progressive text generation
    Wu, Di
    Cheng, Peng
    Zheng, Yuying
    COMPUTER SPEECH AND LANGUAGE, 2025, 89
  • [27] Guesswork for Inference in Machine Translation with Seq2seq Model
    Liu, Lilian
    Malak, Derya
    Medard, Muriel
    2019 IEEE INFORMATION THEORY WORKSHOP (ITW), 2019, : 60 - 64
  • [28] A Method for Estimating Process Maliciousness with Seq2Seq Model
    Tobiyama, Shun
    Yamaguchi, Yukiko
    Hasegawa, Hirokazu
    Shimada, Hajime
    Akiyama, Mitsuaki
    Yagi, Takeshi
    2018 32ND INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN), 2018, : 255 - 260
  • [29] Abstract Text Summarization with a Convolutional Seq2seq Model
    Zhang, Yong
    Li, Dan
    Wang, Yuheng
    Fang, Yang
    Xiao, Weidong
    APPLIED SCIENCES-BASEL, 2019, 9 (08):
  • [30] Map Matching Based on Seq2Seq with Topology Information
    Bai, Yulong
    Li, Guolian
    Lu, Tianxiu
    Wu, Yadong
    Zhang, Weihan
    Feng, Yidan
    APPLIED SCIENCES-BASEL, 2023, 13 (23):