Public
- Public
- Network
- Groups
- Popular
- People

Conversation

Notices

Kenzi NOIKE (mstdn.jp) (求職中) (knoike@mstdn.jp)'s status on Monday, 25-Feb-2019 05:57:37 JST Kenzi NOIKE (mstdn.jp) (求職中)

| [1902.06797] End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model https://arxiv.org/abs/1902.06797
In conversation Monday, 25-Feb-2019 05:57:37 JST from mstdn.jp permalink
Attachments
1. No result found on File_thumbnail lookup.
  
  End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model
  
  from arXiv.org
  
  Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications. Compared to text-to-speech alignment, lyrics alignment remains highly challenging, despite many attempts to combine numerous sub-modules including vocal separation and detection in an effort to break down the problem. Furthermore, training required fine-grained annotations to be available in some form. Here, we present a novel system based on a modified Wave-U-Net architecture, which predicts character probabilities directly from raw audio using learnt multi-scale representations of the various signal components. There are no sub-modules whose interdependencies need to be optimized. Our training procedure is designed to work with weak, line-level annotations available in the real world. With a mean alignment error of 0.35s on a standard dataset our system outperforms the state-of-the-art by an order of magnitude.

Public

Conversation

Notices

Feeds