請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68979
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 黃鐘揚(Chung-Yang Huang) | |
dc.contributor.author | Kuan-Yu Lin | en |
dc.contributor.author | 林冠宇 | zh_TW |
dc.date.accessioned | 2021-06-17T02:45:18Z | - |
dc.date.available | 2020-08-24 | |
dc.date.copyright | 2017-08-24 | |
dc.date.issued | 2017 | |
dc.date.submitted | 2017-08-15 | |
dc.identifier.citation | [1] Peter Potash, Alexey Romanov, and Anna Rumshisky, “GhostWriter: Using an LSTM for Automatic Rap Lyric Generation”, Proc. EMNLP 2015, pp. 1919–1924.
[2] Eric Malmi, Pyry Takala, Hannu Toivonen, Tapani Raiko, and Aristides Gionis, “DopeLearning: A Computational Approach to Rap Lyrics Generation”, KDD 2016. [3] “Deep Beat: Rap Generating AI.” [Online]. Available: http://deepbeat.org/. [4] “『致敬赵雷』基于TensorFlow让机器生成赵雷曲风的歌词” [Online]. Available: https://goo.gl/CxpsQP. [5] 王奕鈞, “神經網路應用於地籍坐標轉換之研究”, 國立政治大學地政學系碩士論文, 2006。 [6] “word2vec傻瓜剖析” [Online]. Available: http://xiaoquanzi.net/?p=156. [7] Denny Britz, “Recurrent Neural Networks Tutorial, Part 1 – Introduction to RNNs” [Online]. Available: http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/. [8] “Understanding LSTM Networks” [Online]. Available: http://colah.github.io/posts/2015-08-Understanding-LSTMs/. [9] “Sequence-to-Sequence Models” [Online]. Available: https://www.tensorflow.org/tutorials/seq2seq#lets_run_it. [10] “jieba 源码解析” [Online]. Available: https://goo.gl/QHJW55. [11] “Pypinyin 0.23.0汉字拼音转换工具” [Online]. Available: https://pypi.python.org/pypi/pypinyin. [12] “IPA Generator (Python 3)” [Online]. Availabe: https://github.com/mphilli/English_to_IPA. [13] Nitesh Pradhan, Manasi Gyanchandani and Rajesh Wadhvani, “A Review on Text Similarity Technique used in IR and its Application”, IJCA 2015. [14] “StreetVoice 街聲” [Online]. Available: https://streetvoice.com/. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68979 | - |
dc.description.abstract | 隨著AI發展,人工智慧作曲日益興盛,在未來人工智慧作詞也應將於人工智慧音樂扮演重要角色,然而現今仍鮮少對於中文歌詞的研究,因此我們在這篇論文提出中文歌詞產生系統,也希望能為這塊領域吸引更多研究。本研究之中文產生系統使用序列學習,不同於常見的使用詞嵌入作輸入輸出,我們還導入了拼音向量,由於現下許多中文歌詞參雜英文,所以我們的拼音向量中文部分為注音,英文部分則轉換成國際音標。最後由實驗結果可以看到,同時使用拼音向量、詞向量和詞嵌入的序列模型可以產生相較於原本只使用詞嵌入的序列模型,明顯順暢的歌詞。 | zh_TW |
dc.description.abstract | With the development of AI, composing music by AI keeps prospering. However, sometimes we struggle with the lyrics, which play an important role to form more delicate expressions. Unfortunately, there are limited researches on lyrics generation. Among these researches, there is only one for Chinese lyrics generation. Since Chinese is the second most used language in the world, there should be a huge demand for Chinese lyrics composition. In our work, we demonstrate how a Chinese lyrics generator based on Sequence to Sequence can support those who are out of ideas for writing Chinese lyrics. Other than typically used word embedding and word2vec, we also introduced a pronunciation vector in our model. Our pronunciation vector consists of Chinese Bopomofo phonetic spelling for Chinese words and International Phonetic Alphabet for English words appearing sometimes in Chinese compositions. Demonstrated by the experimental results, our model with word2vec and pronunciation vector can generate catchier lyrics with fluency. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T02:45:18Z (GMT). No. of bitstreams: 1 ntu-106-R04943148-1.pdf: 1973641 bytes, checksum: 0e3c751d501639d5192da40666e39904 (MD5) Previous issue date: 2017 | en |
dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vi LIST OF TABLES vii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Related Works 1 1.3 Contributions of the Thesis 2 1.4 Organization of the Thesis 2 Chapter 2 Preliminaries 3 2.1 Neural Networks 3 2.2 Word2Vec 8 2.3 Recurrent Neural Networks 9 2.4 Long-Short Term Memory 10 2.5 Sequence-to-Sequence Models 13 Chapter 3 Core Algorithms and Tools introduced in the Chinese Lyrics Generator 15 3.1 Introduction 15 3.2 Jieba 15 3.3 Pypinyin 16 3.4 IPA Generator 17 3.5 Sequence-to-Sequence Model with word2vec 18 3.6 Sequence-to-Sequence with word2vec and Bopomofo 19 3.7 Similarity 20 Chapter 4 Implementation: System Architecture 22 4.1 Overview – System Flow 22 4.2 Crawler 23 4.3 Preprocessing 24 4.4 Feature Select 25 4.5 Sequence-to-Sequence with word2vec 25 4.6 Sequence-to-Sequence with word2vec and Bopomofo 28 4.7 Association with Database Lyrics 29 4.8 Issue: RNN sticks at the Same Value 29 Chapter 5 Experimental Results 30 5.1 Sequence-to-Sequence with word2vec 30 5.2 Sequence-to-Sequence with word2vec and Bopomofo 33 Chapter 6 Conclusions and Future Work 37 6.1 Conclusions 37 6.2 Future Work 37 REFERENCE 39 | |
dc.language.iso | en | |
dc.title | 運用序列學習為基礎之中文歌詞產生系統 | zh_TW |
dc.title | Chinese Lyrics Generation using Sequence to Sequence Learning Approach | en |
dc.type | Thesis | |
dc.date.schoolyear | 105-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 許萬寶(Wan-Pao Hsu),李宏毅(Hung-Yi Lee),周俊男(Chun-Nan Chou) | |
dc.subject.keyword | 歌詞,序列學習, | zh_TW |
dc.subject.keyword | Lyrics,Sequence to sequence, | en |
dc.relation.page | 40 | |
dc.identifier.doi | 10.6342/NTU201703342 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2017-08-16 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-106-1.pdf 目前未授權公開取用 | 1.93 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。