paper-with-me

홈 › Papers

Sequence Generation using Deep Recurrent Networks and Embeddings: A study case in music

2020-12-02 · Sebastian Garcia-Valencia, Alejandro Betancourt, Juan G. Lalinde-Pulido

Automatic generation of sequences has been a highly explored field in the last years. In particular, natural language processing and automatic music composition have gained importance due to the recent advances in machine learning and Neural Networks with intrinsic memory mechanisms such as Recurrent Neural Networks. This paper evaluates different types of memory mechanisms (memory cells) and analyses their performance in the field of music composition. The proposed approach considers music theory concepts such as transposition, and uses data transformations (embeddings) to introduce semantic meaning and improve the quality of the generated melodies. A set of quantitative metrics is presented to evaluate the performance of the proposed architecture automatically, measuring the tonality of the musical compositions.

📄 PDF Abstract BibTeX arXiv:2012.01231

Code (1)

sebasgverde/mono-midi-transposition-dataset

Similar Papers 제목 키워드 기반

Semi-supervised sequence tagging with bidirectional language models

2017-04-29 · ACL 2017 7 · Matthew E. Peters, Waleed Ammar, Chandra Bhagavatula, Russell Power

Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representa…

Chunkingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1

On the Use of Word Embeddings Alone to Represent Natural Language Sequences

2018-01-01 · ICLR 2018 1 · Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min 외

To construct representations for natural language sequences, information from two main sources needs to be captured: (i) semantic meaning of individual words, and (ii) their compositionality. These two types of informati…

SentenceWord Embeddings

Predefined Sparseness in Recurrent Sequence Models

2018-08-27 · CONLL 2018 10 · Thomas Demeester, Johannes Deleu, Fréderic Godin, Chris Develder

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense mo…

Language ModelingLanguage ModellingWord Embeddings

Return of the RNN: Residual Recurrent Networks for Invertible Sentence Embeddings

2023-03-23 · Jeremy Wilkerson

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation…

Machine TranslationSentenceSentence EmbeddingsTranslation

Every Smile is Unique: Landmark-Guided Diverse Smile Generation

2018-02-06 · CVPR 2018 6 · Wei Wang, Xavier Alameda-Pineda, Dan Xu, Pascal Fua 외

Each smile is unique: one person surely smiles in different ways (e.g., closing/opening the eyes or mouth). Given one input image of a neutral face, can we generate multiple smile videos with distinctive characteristics?…

Video Generation