In this paper, we propose to adapt the method of mutual information maximization into the task of Chinese lyrics conditioned melody generation to improve the generation quality and diversity. We employ scheduled sampling and force decoding techniques to improve the alignment between lyrics and melodies. With our method, which we called Diverse Melody Generation (DMG), a sequence-to-sequence model learns to generate diverse melodies heavily depending on the input style ids, while keeping the tonality and improving the alignment. The experimental results of subjective tests show that DMG can generate more pleasing and coherent tunes than baseline methods.
Zhejiang University（浙江大学）；Microsoft Research Asia（微软亚洲研究院）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Lyric-to-melody generation, which generates melody according to given lyrics, is one of the most important automatic music composition tasks. With the rapid development of deep learning, previous works address this task with end-to-end neural network models. However, deep learning models cannot well capture the strict but subtle relationships between lyrics and melodies, which compromises the harmony between lyrics and generated melodies. In this paper, we propose ReLyMe, a method that incorporates Relationships between Lyrics and Melodies from music theory to ensure the harmony between lyrics…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Zhejiang University（浙江大学）
Lyric-to-melody generation is an important task in automatic songwriting. Previous lyric-to-melody generation systems usually adopt end-to-end models that directly generate melodies from lyrics, which suffer from several issues: 1) lack of paired lyric-melody training data; 2) lack of control on generated melodies. In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e.g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i.e., the system consists of a lyric-to-template module and a templ…
Renmin University of China（中国人民大学）；Microsoft Research Asia（微软亚洲研究院）
Lyric-to-melody generation is an important task in songwriting, and is also quite challenging due to its unique characteristics: the generated melodies should not only follow good musical patterns, but also align with features in lyrics such as rhythms and structures. These characteristics cannot be well handled by neural generation models that learn lyric-to-melody mapping in an end-to-end way, due to several issues: (1) lack of aligned lyric-melody training data to sufficiently learn lyric-melody feature alignment; (2) lack of controllability in generation to better and explicitly align the …
National Engineering Research Center for Software Engineering, Peking University（北京大学软件工程国家工程研究中心）；Nanjing University of Science and Technology（南京理工大学）；Microsoft Research Asia（微软亚洲研究院）；Zhejiang University（浙江大学）
Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry. In automatic song writing, lyric-to-melody generation and melody-to-lyric generation are two important tasks, both of which usually suffer from the following challenges: 1) the paired lyric and melody data are limited, which affects the generation quality of the two tasks, considering a lot of paired training data are needed due to the weak correlation between lyric and melody; 2) Strict alignments are required between lyric and melody, which relies on sp…
National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）；The University of Electro-Communications（电气通信大学）
We propose a deep attention-based alignment network, which aims to automatically predict lyrics and melody with given incomplete lyrics as input in a way similar to the music creation of humans. Most importantly, a deep neural lyrics-to-melody net is trained in an encoder-decoder way to predict possible pairs of lyrics-melody when given incomplete lyrics (few keywords). The attention mechanism is exploited to align the predicted lyrics with the melody during the lyrics-to-melody generation. The qualitative and quantitative evaluation metrics reveal that the proposed method is indeed capable of…
National Institute of Informatics（国立情报学研究所）；Indraprastha Institute of Information Technology Delhi（德里印度信息技术学院）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables to learn and discover latent relationship between interesting lyrics and accompanying melody. Unfortunately, the limited availability of paired lyrics-melody dataset with alignment information has hindered the research progress. To address this problem, we create a large dataset consisting of 12,197 MIDI songs each with paired lyrics and melody alignment through leveraging different music sources where alignment relationship between syllables and music attributes…
National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）
Generating melody from lyrics is an interesting yet challenging task in the area of artificial intelligence and music. However, the difficulty of keeping the consistency between input lyrics and generated melody limits the generation quality of previous works. In our proposal, we demonstrate our proposed interpretable lyrics-to-melody generation system which can interact with users to understand the generation process and recreate the desired songs. To improve the reliability of melody generation that matches lyrics, mutual information is exploited to strengthen the consistency between lyrics …
Creating a pop song melody according to pre-written lyrics is a typical practice for composers. A computational model of how lyrics are set as melodies is important for automatic composition systems, but an end-to-end lyric-to-melody model would require enormous amounts of paired training data. To mitigate the data constraints, we adopt a two-stage approach, dividing the task into lyric-to-rhythm and rhythm-to-melody modules. However, the lyric-to-rhythm task is still challenging due to its multimodality. In this paper, we propose a novel lyric-to-rhythm framework that includes part-of-speech …
Recent studies in singing voice synthesis have achieved high-quality results leveraging advances in text-to-speech models based on deep neural networks. One of the main issues in training singing voice synthesis models is that they require melody and lyric labels to be temporally aligned with audio data. The temporal alignment is a time-exhausting manual work in preparing for the training data. To address the issue, we propose a melody-unsupervision model that requires only audio-and-lyrics pairs without temporal alignment in training time but generates singing voice audio given a melody and l…
MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling
Graduate School of Artificial Intelligence, KAIST, South Korea（韩国釜山科学技术院人工智能研究生院）；Graduate School of Culture Technology, KAIST, South Korea（韩国釜山科学技术院文化科技研究生院）
Indian Institute of Technology, Kharagpur（印度理工学院克勒格布尔分校）；National Institute of Informatics（国立信息学研究所）；ISIMA；The University of Electro-Communications（电气通信大学）；EPFL（洛桑联邦理工学院）
In this paper, we propose a technique to address the most challenging aspect of algorithmic songwriting process, which enables the human community to discover original lyrics, and melodies suitable for the generated lyrics. The proposed songwriting system, Automatic Neural Lyrics and Melody Composition (AutoNLMC) is an attempt to make the whole process of songwriting automatic using artificial neural networks. Our lyric to vector (lyric2vec) model trained on a large set of lyric-melody pairs dataset parsed at syllable, word and sentence levels are large scale embedding models enable us to trai…
Song translation requires both translation of lyrics and alignment of music notes so that the resulting verse can be sung to the accompanying melody, which is a challenging problem that has attracted some interests in different aspects of the translation process. In this paper, we propose Lyrics-Melody Translation with Adaptive Grouping (LTAG), a holistic solution to automatic song translation by jointly modeling lyrics translation and lyrics-melody alignment. It is a novel encoder-decoder framework that can simultaneously translate the source lyrics and determine the number of aligned notes a…
Center for Music Technology Georgia Institute of Technology（佐治亚理工学院音乐技术中心）
Automatic lyrics generation has received attention from both music and AI communities for years. Early rule-based approaches have~---due to increases in computational power and evolution in data-driven models---~mostly been replaced with deep-learning-based systems. Many existing approaches, however, either rely heavily on prior knowledge in music and lyrics writing or oversimplify the task by largely discarding melodic information and its relationship with the text. We propose an end-to-end melody-conditioned lyrics generation system based on Sequence Generative Adversarial Networks (SeqGAN),…
The goal of this paper is twofold. First, we introduce DALI, a large and rich multimodal dataset containing 5358 audio tracks with their time-aligned vocal melody notes and lyrics at four levels of granularity. The second goal is to explain our methodology where dataset creation and learning models interact using a teacher-student machine learning paradigm that benefits each other. We start with a set of manual annotations of draft time-aligned lyrics and notes made by non-expert users of Karaoke games. This set comes without audio. Therefore, we need to find the corresponding audio and adapt …
Sorbonne Université（索邦大学）；Grenoble-INP - Institut Polytechnique de Grenoble（格勒诺布尔理工学院）；Télécom Paris - Institut Polytechnique de Paris（巴黎电信学院 - 巴黎理工学院）；Spotify；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；I3S（I3S实验室）；ISIR（智能系统与机器人研究所）；Universitat Pompeu Fabra（庞培法布拉大学）；MTG（音乐技术组）；Centre Inria Nancy - Grand Est（法国国家信息与自动化研究院南锡-大东部研究中心）
This dissertation proposes the study of multimodal learning in the context of musical signals. Throughout, we focus on the interaction between audio signals and text information. Among the many text sources related to music that can be used (e.g. reviews, metadata, or social network feedback), we concentrate on lyrics. The singing voice directly connects the audio signal and the text information in a unique way, combining melody and lyrics where a linguistic dimension complements the abstraction of musical instruments. Our study focuses on the audio and lyrics interaction for targeting source …
Version identification (VI) has seen substantial progress over the past few years. On the one hand, the introduction of the metric learning paradigm has favored the emergence of scalable yet accurate VI systems. On the other hand, using features focusing on specific aspects of musical pieces, such as melody, harmony, or lyrics, yielded interpretable and promising performances. In this work, we build upon these recent advances and propose a metric learning-based system systematically leveraging four dimensions commonly admitted to convey musical similarity between versions: melodic line, harmon…
Ping An Technology (Shenzhen) Co., Ltd（平安科技（深圳）有限公司）
This paper presents a novel, syllable-structured Chinese lyrics generation model given a piece of original melody. Most previously reported lyrics generation models fail to include the relationship between lyrics and melody. In this work, we propose to interpret lyrics-melody alignments as syllable structural information and use a multi-channel sequence-to-sequence model with considering both phrasal structures and semantics. Two different RNN encoders are applied, one of which is for encoding syllable structures while the other for semantic encoding with contextual sentences or input keywords…
Zhejiang University（浙江大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft STC Asia（微软亚洲互联网工程院）
In this paper, we develop DeepSinger, a multi-lingual multi-singer singing voice synthesis (SVS) system, which is built from scratch using singing training data mined from music websites. The pipeline of DeepSinger consists of several steps, including data crawling, singing and accompaniment separation, lyrics-to-singing alignment, data filtration, and singing modeling. Specifically, we design a lyrics-to-singing alignment model to automatically extract the duration of each phoneme in lyrics starting from coarse-grained sentence level to fine-grained phoneme level, and further design a multi-l…
Peking University（北京大学）；Wangxuan Institute of Computer Technology, PKU（北京大学王选计算机研究所）；China Conservatory of Music（中国音乐学院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Unlike melody extraction and other aspects of music transcription, research on playing technique detection is still in its early stages. Compared to existing work mostly focused on playing technique detection for individual single notes, we propose a general end-to-end method based on Sound Event Detection by FCN for musical instrument playing technique detection. In our case, we choose Erhu, a well-known Chinese bowed-stringed instrument, to experiment with our method. Because of the limitation of FCN, we present an algorithm to detect on variable length audio. The effectiveness of the propos…
Tongji University（同济大学）；Shanghai Institute of Visual Arts（上海视觉艺术学院）；Northwestern Polytechnical University（西北工业大学）；NetEase Inc.（网易公司）
This paper introduces Opencpop, a publicly available high-quality Mandarin singing corpus designed for singing voice synthesis (SVS). The corpus consists of 100 popular Mandarin songs performed by a female professional singer. Audio files are recorded with studio quality at a sampling rate of 44,100 Hz and the corresponding lyrics and musical scores are provided. All singing recordings have been phonetically annotated with phoneme boundaries and syllable (note) boundaries. To demonstrate the reliability of the released data and to provide a baseline for future research, we built baseline deep …
Beijing University of Posts and Telecommunications（北京邮电大学）
Music generation has always been a hot topic. When discussing symbolic music, melody or harmonies are usually seen as the only generating targets. But in fact, playing techniques are also quite an important part of the music. In this paper, we discuss the playing techniques generation problem by seeing it as a tagging problem. We propose a model that can use both the current data and external knowledge. Experiments were carried out by applying the proposed model in Chinese bamboo flute music, and results show that our method can make generated music more lively.
Structure is one of the most essential aspects of music, and music structure is commonly indicated through repetition. However, the nature of repetition and structure in music is still not well understood, especially in the context of music generation, and much remains to be explored with Music Information Retrieval (MIR) techniques. Analyses of two popular music datasets (Chinese and American) illustrate important music construction principles: (1) structure exists at multiple hierarchical levels, (2) songs use repetition and limited vocabulary so that individual songs do not follow general s…
