Long short-term memory

Résumé

Long short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods. It aims to provide a short-term memory for RNN that can last thousands of timesteps, thus "long short-term memory". It is applicable to classification, processing and predicting data based on time series, such as in handwriting, speech recognition, machine translation, speech activity detection, robot control, video games, and healthcare. A common LSTM unit is composed of a cell, an input gate, an output gate and a forget

Source officielle

https://en.wikipedia.org/wiki/Long_short-term_memory

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (87)

Chargement

Afficher plus

Publications associées

Chargement

Personnes associées (8)

Personnes associées

Chargement

Unités associées (1)

Unités associées

Chargement

Concepts associés (22)

Un réseau de neurones récurrents (RNN pour recurrent neural network en anglais) est un réseau de neurones artificiels présentant des connexions récurrentes. Un réseau de neurones récurrents est const

L'apprentissage profond ou apprentissage en profondeur (en anglais : deep learning, deep structured learning, hierarchical learning) est un sous-domaine de l’intelligence artificiel

vignette|redresse=0.8|Les assistants personnels intelligents sont l'une des applications concrètes de l'intelligence artificielle dans les années 2010. L'intelligence artificielle (IA) est un ensembl

Afficher plus

Concepts associés

Chargement

Cours associés (19)

Cours associés

Chargement

Séances de cours associées (45)

Séances de cours associées

Chargement

Publications associées (87)

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.

2021

Chargement

Probabilistic models for music

Jean-François Paiement

This thesis proposes to analyse symbolic musical data under a statistical viewpoint, using state-of-the-art machine learning techniques. Our main argument is to show that it is possible to design generative models that are able to predict and to generate music given arbitrary contexts in a genre similar to a training corpus, using a minimal amount of data. For instance, a carefully designed generative model could guess what would be a good accompaniment for a given melody. Conversely, we propose generative models in this thesis that can be sampled to generate realistic melodies given harmonic context. Most computer music research has been devoted so far to the direct modeling of audio data. However, most of the music models today do not consider the musical structure at all. We argue that reliable symbolic music models such a the ones presented in this thesis could dramatically improve the performance of audio algorithms applied in more general contexts. Hence, our main contributions in this thesis are three-fold: We have shown empirically that long term dependencies are present in music data and we provide quantitative measures of such dependencies; We have shown empirically that using domain knowledge allows to capture long term dependencies in music signal better than with standard statistical models for temporal data. We describe many probabilistic models aimed to capture various aspects of symbolic polyphonic music. Such models can be used for music prediction. Moreover, these models can be sampled to generate realistic music sequences; We designed various representations for music that could be used as observations by the proposed probabilistic models.

École Polytechnique Fédérale de Lausanne2008

Chargement

Probabilistic models for music

Jean-François Paiement

EPFL2008

Chargement

Afficher plus