Algorithmic Songwriting with ALYSIA

Ackerman, Margareta; Loker, David

doi:10.1007/978-3-319-55750-2_1

Cited by 20 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three stylistic categories such as nursery rhymes, folk songs, and rock songs are generated for given lyrics. A recently proposed ALYSIA songwriting system [8] is a lyrics-conditioned melody generation system based on exploiting a random forest model, which can predict the pitch and rhythm of notes to determine the accompaniments for lyrics. When given Chinese lyrics, melody and exact alignment are predicted in a lyrics-conditional melody composition framework [9], which is an end-to-end neural network model including RNN-based lyrics encoder, RNNbased context melody encoder, and a hierarchical RNN decoder.…”

Section: Related Workmentioning

confidence: 99%

“…Generating a melody from lyrics is to predict a melodic sequence when given lyrics as a condition. Existing works, e.g., Markov models [7], random forests [8], and recurrent neural network (RNN) [9], can generate lyrics-conditioned music melody. However, these methods cannot ensure that the distribution of generated data is consistent with that of real samples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Conditional LSTM-GAN for Melody Generation from Lyrics

Srivastava

Canales

2021

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables us to learn and discover latent relationships between interesting lyrics and accompanying melodies. Unfortunately, the limited availability of a 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 is extracted. Most importantly, we propose a novel deep generative model, conditional Long Short-Term Memory (LSTM)–Generative Adversarial Network for melody generation from lyrics, which contains a deep LSTM generator and a deep LSTM discriminator both conditioned on lyrics. In particular, lyrics-conditioned melody and alignment relationship between syllables of given lyrics and notes of predicted melody are generated simultaneously. Extensive experimental results have proved the effectiveness of our proposed lyrics-to-melody generative model, where plausible and tuneful sequences can be inferred from lyrics.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Conditional LSTM-GAN for Melody Generation from Lyrics

Srivastava

Canales

2021

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

show abstract

“…For modelling temporal dependencies, Markov models are considered the first choice since the very early stages of music generation [14]. One of more the recent works using this principle is the ALYSIA system [1] that creates both lyrics and melodies.…”

Section: Melody Generation Systemsmentioning

confidence: 99%

“…Given a sentence S which contains N words w i , that is, S =< w 1 , w 2 , ..., w n >∈ V n , V n is the size of the overall vocabulary. The language model aims to find the probability distribution of the sentence, which can be formalised using the equation (1). Given the forward sequence of a word, the probability of the entire word sequence can be decomposed into the product of the conditional probability of the next word with respect to its forward word.…”

Section: Computer-generated Melodiesmentioning

confidence: 99%

A novel dataset for the identification of computer generated melodies in the CSMT challenge

Li,

Jing,

Fazekas

2020

Preprint

View full text Add to dashboard Cite

This paper introduces a novel dataset for the identification of computer generated melodies as used in the data challenge organised by the Conference on Sound and Music Technology (CSMT). The CSMT data challenge requires participants to identify whether a given piece of melody is generated by computer or is composed by human. The dataset consists of two parts: a development dataset and an evaluation dataset. The development dataset contains only computer generated melodies whereas the evaluation dataset contain both computer generated melodies and human composed melodies. The aim of the dataset is to facilitate the develpment and assessment of methods to identified computer generated melodies and facilitate the creation of generative music systems.

show abstract

“…There are several existing research works on generating lyrics-conditional melody (Ackerman and Loker 2017;Scirea et al 2015;Monteith, Martinez, and Ventura 2012;Fukayama et al 2010 Figure 1: A fragment of a Chinese song "Drunken Concubine (new version)". The blue rectangles indicate rests, some intervals of silence in a piece of melody.…”

Section: Introductionmentioning

confidence: 99%

Neural Melody Composition from Lyrics

Bao

Huang

Wei

et al. 2019

Natural Language Processing and Chinese Computing

View full text Add to dashboard Cite

In this paper, we study a novel task that learns to compose music from natural language. Given the lyrics as input, we propose a melody composition model that generates lyricsconditional melody as well as the exact alignment between the generated melody and the given lyrics simultaneously. More specifically, we develop the melody composition model based on the sequence-to-sequence framework. It consists of two neural encoders to encode the current lyrics and the context melody respectively, and a hierarchical decoder to jointly produce musical notes and the corresponding alignment. Experimental results on lyrics-melody pairs of 18,451 pop songs demonstrate the effectiveness of our proposed methods. In addition, we apply a singing voice synthesizer software to synthesize the "singing" of the lyrics and melodies for human evaluation. Results indicate that our generated melodies are more melodious and tuneful compared with the baseline method. A syllable is a word or part of a word which contains a single vowel sound and that is pronounced as a unit. Chinese is a monosyllabic language which means words (Chinese characters) predominantly consist of a single syllable (https://en.wikipedia. org/wiki/Monosyllabic_language).

show abstract

Algorithmic Songwriting with ALYSIA

Cited by 20 publications

References 3 publications

Conditional LSTM-GAN for Melody Generation from Lyrics

Conditional LSTM-GAN for Melody Generation from Lyrics

A novel dataset for the identification of computer generated melodies in the CSMT challenge

Neural Melody Composition from Lyrics

Contact Info

Product

Resources

About