
SongTrans is a unified model that can directly transcribe and align song lyrics and musical notes without requiring pre-processing or separate tools.


coremsg

songtrans-a-unified-model-for-automatic-transcription-and-alignment-of-song-lyrics-and-musical-notes


SongTrans: A Unified Model for Automatic Transcription and Alignment of Song Lyrics and Musical Notes


title_rewrite


The authors introduce S2Cap, a novel dataset for the task of singing style captioning, which aims to generate textual descriptions of the vocal and musical characteristics of singing voices. The dataset contains a diverse set of attributes, including pitch, volume, tempo, mood, singer's gender and age, and musical genre and emotional expression.


constructing-a-comprehensive-dataset-for-singing-style-captioning


Constructing a Comprehensive Dataset for Singing Style Captioning



CONTUNER, a diffusion-based model, can efficiently beautify amateur singing voices by correcting pitch and enhancing expressiveness without requiring paired professional-amateur data.


singing-voice-beautification-with-pitch-correction-and-expressiveness-enhancement


Singing Voice Beautification with Pitch Correction and Expressiveness Enhancement
