Constructing a Singing Style Caption Dataset

• URL: http://arxiv.org/abs/2409.09866v1
• Date: Sun, 15 Sep 2024 21:19:24 GMT
• Title: Constructing a Singing Style Caption Dataset
• Authors: Hyunjong Ok, Jaeho Lee,
• Abstract summary: We introduce S2Cap, an audio-text pair dataset with a diverse set of attributes. S2Cap consists of pairs of textual prompts and music audio samples with a wide range of vocal and musical attributes. We present a novel mechanism called CRESCENDO, which utilizes positive-pair similarity learning to synchronize the embedding spaces of a pretrained audio encoder.
• Score: 12.515874333424929
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Singing voice synthesis and conversion have emerged as significant subdomains of voice generation, leading to much demands on prompt-conditioned generation. Unlike common voice data, generating a singing voice requires an understanding of various associated vocal and musical characteristics, such as the vocal tone of the singer or emotional expressions. However, existing open-source audio-text datasets for voice generation tend to capture only a very limited range of attributes, often missing musical characteristics of the audio. To fill this gap, we introduce S2Cap, an audio-text pair dataset with a diverse set of attributes. S2Cap consists of pairs of textual prompts and music audio samples with a wide range of vocal and musical attributes, including pitch, volume, tempo, mood, singer's gender and age, and musical genre and emotional expression. Utilizing S2Cap, we suggest an effective novel baseline algorithm for singing style captioning. Singing style captioning is a relative task to voice generation that generates text descriptions of vocal characteristics, which we first suggested. First, to mitigate the misalignment between the audio encoder and the text decoder, we present a novel mechanism called CRESCENDO, which utilizes positive-pair similarity learning to synchronize the embedding spaces of a pretrained audio encoder to get similar embeddings with a text encoder. We additionally supervise the model using the singer's voice, which is demixed by the accompaniment. This supervision allows the model to more accurately capture vocal characteristics, leading to improved singing style captions that better reflect the style of the singer. The dataset and the codes are available at \bulurl{https://github.com/HJ-Ok/S2cap}.

Related papers

• TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control [58.96445085236971]
  Zero-shot singing voice synthesis (SVS) with style transfer and style control aims to generate high-quality singing voices with unseen timbres and styles. We introduce TCSinger, the first zero-shot SVS model for style transfer across cross-lingual speech and singing styles. We show that TCSinger outperforms all baseline models in quality synthesis, singer similarity, and style controllability across various tasks.
  arXiv  Detail & Related papers  (2024-09-24T11:18:09Z)
• Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment [56.019288564115136]
  We propose a novel task called text-to-song synthesis which incorporating both vocals and accompaniments generation. We develop Melodist, a two-stage text-to-song method that consists of singing voice synthesis (SVS) and vocal-to-accompaniment (V2A) synthesis. evaluation results on our dataset demonstrate that Melodist can synthesize songs with comparable quality and style consistency.
  arXiv  Detail & Related papers  (2024-04-14T18:00:05Z)
• Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt [50.25271407721519]
  We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation. Experiments show that our model achieves favorable controlling ability and audio quality.
  arXiv  Detail & Related papers  (2024-03-18T13:39:05Z)
• Singer Identity Representation Learning using Self-Supervised Techniques [0.0]
  We propose a framework for training singer identity encoders to extract representations suitable for various singing-related tasks. We explore different self-supervised learning techniques on a large collection of isolated vocal tracks. We evaluate the quality of the resulting representations on singer similarity and identification tasks.
  arXiv  Detail & Related papers  (2024-01-10T10:41:38Z)
• StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis [63.18764165357298]
  Style transfer for out-of-domain singing voice synthesis (SVS) focuses on generating high-quality singing voices with unseen styles. StyleSinger is the first singing voice synthesis model for zero-shot style transfer of out-of-domain reference singing voice samples. Our evaluations in zero-shot style transfer undeniably establish that StyleSinger outperforms baseline models in both audio quality and similarity to the reference singing voice samples.
  arXiv  Detail & Related papers  (2023-12-17T15:26:16Z)
• Make-A-Voice: Unified Voice Synthesis With Discrete Representation [77.3998611565557]
  Make-A-Voice is a unified framework for synthesizing and manipulating voice signals from discrete representations. We show that Make-A-Voice exhibits superior audio quality and style similarity compared with competitive baseline models.
  arXiv  Detail & Related papers  (2023-05-30T17:59:26Z)
• A Melody-Unsupervision Model for Singing Voice Synthesis [9.137554315375919]
  We propose a melody-unsupervision model that requires only audio-and-lyrics pairs without temporal alignment in training time. We show that the proposed model is capable of being trained with speech audio and text labels but can generate singing voice in inference time.
  arXiv  Detail & Related papers  (2021-10-13T07:42:35Z)
• DeepSinger: Singing Voice Synthesis with Data Mined From the Web [194.10598657846145]
  DeepSinger is a multi-lingual singing voice synthesis system built from scratch using singing training data mined from music websites. We evaluate DeepSinger on our mined singing dataset that consists of about 92 hours data from 89 singers on three languages.
  arXiv  Detail & Related papers  (2020-07-09T07:00:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.