Mstre-net: Multistreaming Acoustic Modeling For Automatic Lyrics Transcription
2021 · Emir Demirel, Sven Ahlbäck, Simon Dixon
Abstract
This paper makes several contributions to automatic lyrics transcription (ALT) research. Our main contribution is a novel variant of the Multistreaming Time-Delay Neural Network (MTDNN) architecture, called MSTRE-Net, which processes the temporal information using multiple streams in parallel with varying resolutions keeping the network more compact, and thus with a faster inference and an improved recognition rate than having identical TDNN streams. In addition, two novel preprocessing steps prior to training the acoustic model are proposed. First, we suggest using recordings from both monophonic and polyphonic domains during training the acoustic model. Second, we tag monophonic and polyphonic recordings with distinct labels for discriminating non-vocal silence and music instances during alignment. Moreover, we present a new test set with a considerably larger size and a higher musical variability compared to the existing datasets used in ALT literature, while maintaining the gender
Authors
(none)
Tags
Stats
Related papers
- MM-ALT: A Multimodal Automatic Lyric Transcription System (2022)8.35
- Yourmt3+: Multi-instrument Music Transcription With Enhanced Transformer Architectures And Cross-dataset Stem Augmentation (2024)11.84
- Towards Building An End-to-end Multilingual Automatic Lyrics Transcription Model (2024)0.00
- Automatic Lyrics Transcription Using Dilated Convolutional Neural Networks With Self-attention (2020)10.07
- Htmd-net: A Hybrid Masking-denoising Approach To Time-domain Monaural Singing Voice Separation (2021)2.26
- Annotation-free Automatic Music Transcription With Scalable Synthetic Data And Adversarial Domain Confusion (2023)4.52
- End-to-end Lyrics Alignment For Polyphonic Music Using An Audio-to-character Recognition Model (2019)13.11
- Pdaugment: Data Augmentation By Pitch And Duration Adjustments For Automatic Lyrics Transcription (2021)0.00