Results 21 to 30 of about 529 (187)

Aimeric de Peguillan, "En aquelh temps que·l reys mori N’Anfos" (BdT 10.26) [PDF]

Lecturae Tropatorum, 2019
This article proposes a new reading of En aquel temps que·l reis mori n’Anfos and focuses on the author’s point of view, describing the possible circumstances in which the song was composed.
Francesco Saverio Annunziata
doaj  

Marcabru, "Ueimai dey esser alegrans" (BdT 293.34) [PDF]

Lecturae Tropatorum, 2019
To go by its manuscript tradition, vers n. 34 of Marcabru’s lyric corpus had limited success (only two songbooks: CR), but there have been many interventions aimed at shedding light on the identity of the Cabrieyra to whom the Gascon troubadour sent his ...
Samuele Maria Visalli
doaj  

Bertran de Born, "Ara sai eu de prez qals l’a plus gran" (BdT 80.4) [PDF]

Lecturae Tropatorum, 2019
The Crusade song Ara sai eu presents two different versions, one trasmitted by DcFIKd, and the other by M. The M version is curiously preceded by two stanzas addressed to the jongleur Fuilheta (Fuilheta, vos mi preiatz qe ieu chan, BdT 80.17), while the ...
Francesca Sanguineti
doaj  

TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method [PDF]

arXiv, 2021
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,
arxiv  

Raimbaut de Vaqueiras, "Savis e fols, humils et orgoillos" (BdT 392.28) [PDF]

Lecturae Tropatorum, 2019
The main aim of this study is to investigate the rhetorical devices involved in the building of the opposita which, from the first cobla onwards, continue over the next stanzas — with special attention to the pairs of antonyms savis ~ fols, humils ...
Giovanni Borriero
doaj  

Deep Attention-Based Alignment Network for Melody Generation from Incomplete Lyrics [PDF]

arXiv, 2023
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 ...
arxiv  

Raimbaut de Vaqueiras (?), “Altas undas que venez suz la mar” (BdT 392.5a) [PDF]

Lecturae Tropatorum, 2008
The article proposes a new authorship for Altas undas que venez suz la mar, a poem attributed by ms. Sg to Raimbaut de Vaqueiras. This authorship has long been debated by scholars.
Giuseppe Tavani
doaj  

LOAF-M2L: Joint Learning of Wording and Formatting for Singable Melody-to-Lyric Generation [PDF]

arXiv, 2023
Despite previous efforts in melody-to-lyric generation research, there is still a significant compatibility gap between generated lyrics and melodies, negatively impacting the singability of the outputs. This paper bridges the singability gap with a novel approach to generating singable lyrics by jointly Learning wOrding And Formatting during Melody-to-
arxiv  

Lyric Video Analysis Using Text Detection and Tracking [PDF]

arXiv, 2020
We attempt to recognize and track lyric words in lyric videos. Lyric video is a music video showing the lyric words of a song. The main characteristic of lyric videos is that the lyric words are shown at frames synchronously with the music. The difficulty of recognizing and tracking the lyric words is that (1) the words are often decorated and ...
arxiv  

A Computational Evaluation Framework for Singable Lyric Translation [PDF]

arXiv, 2023
Lyric translation plays a pivotal role in amplifying the global resonance of music, bridging cultural divides, and fostering universal connections. Translating lyrics, unlike conventional translation tasks, requires a delicate balance between singability and semantics.
arxiv