On the Improvement of Singing Voice Separation for Monaural Recordings Using the MIR-1K Dataset

Hsu, Chao-Ling; Jang, Jyh-Shing Roger

doi:10.1109/tasl.2009.2026503

Cited by 165 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It consists of various instrumental sounds and singing voices with the F0 annotations. • MIR-1k (MIR) [31] contains 133 minutes of singing voices (11 males, 8 females) recorded with the musical accompaniment, and pitch annotations. We splitted the datasets into training, validation, and test sets in ratio of 3:1:1, except for the VCTK dataset.…”

Section: Methodsmentioning

confidence: 99%

Evaluating the General Education System at Yonsei University, South Korea

Chung

Kim

Yang

et al. 2018

Education Innovation Series

View full text Add to dashboard Cite

We introduce Multi-level feature Fusion-based Periodicity Analysis Model (MF-PAM), a novel deep learning-based pitch estimation model that accurately estimates pitch trajectory in noisy and reverberant acoustic environments. Our model leverages the periodic characteristics of audio signals and involves two key steps: extracting pitch periodicity using periodic non-periodic convolution (PNP-Conv) blocks and estimating pitch by aggregating multi-level features using a modified bidirectional feature pyramid network (BiFPN). We evaluate our model on speech and music datasets and achieve superior pitch estimation performance compared to state-of-the-art baselines while using fewer model parameters. Our model achieves 99.20 % accuracy in pitch estimation on a clean musical dataset. Overall, our proposed model provides a promising solution for accurate pitch estimation in challenging acoustic environments and has potential applications in audio signal processing.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluating the General Education System at Yonsei University, South Korea

Chung

Kim

Yang

et al. 2018

Education Innovation Series

View full text Add to dashboard Cite

show abstract

“…Each clip is stereo, with one channel for singing voice and another for accompaniment. The 1000 clips were sung by 11 male and 8 female amateurs [31].…”

Section: Experiments Parepare Datasetsmentioning

confidence: 99%

3 Directional Inception-ResUNet: deep spatial feature learning for multichannel singing voice separation with distortion

Wang

Sun

2023

Preprint

View full text Add to dashboard Cite

Singing voice separation on robots faces the problem of interpreting ambiguous auditory signals. The acoustic signal, which the humanoid robot perceives through its onboard microphones, is a mixture of singing voice, music, and noise, with distortion, attenuation, and reverberation. In this paper, we used the 3 directional Inception-Resnet structure in the U-shaped encoding and decoding network to improve the utilization of the spatial and spectral information of the spectrograms. Multi-objectives were used to train the model: magnitude consistency loss, phase consistency loss, and magnitude correlation consistency loss. We recorded the singing voice and accompaniment derived from the MIR-1k datasets with NAO robots and synthesized the 10-channel datasets for training the model. The experimental results show that the proposed model trained by multi-objective reaches an average NSDR of 11.55db on the test datasets, which outperforms the comparison model.

show abstract

“…The training data includes labeled data from TONAS (Mora et al, 2010) and unlabeled data from MIR-1K (Hsu & Jang, 2009). The model yields the SoTA F1-score of 68.4% evaluated with the ISMIR2014 dataset (Molina et al, 2014).…”

Section: Vocal Transcription In Polyphonic Musicmentioning

confidence: 99%

Omnizart: A General Toolbox for Automatic Music Transcription

Wu¹,

Luo²,

Tsung-Ping³

et al. 2021

JOSS

View full text Add to dashboard Cite

We present and release Omnizart, a new Python library that provides a streamlined solution to automatic music transcription (AMT). Omnizart encompasses modules that construct the life-cycle of deep learning-based AMT, and is designed for ease of use with a compact command-line interface. To the best of our knowledge, Omnizart is the first toolkit that offers transcription models for various music content including piano solo, instrument ensembles, percussion and vocal. Omnizart also supports models for chord recognition and beat/downbeat tracking, which are highly related to AMT.

show abstract

On the Improvement of Singing Voice Separation for Monaural Recordings Using the MIR-1K Dataset

Cited by 165 publications

References 13 publications

Evaluating the General Education System at Yonsei University, South Korea

Evaluating the General Education System at Yonsei University, South Korea

3 Directional Inception-ResUNet: deep spatial feature learning for multichannel singing voice separation with distortion

Omnizart: A General Toolbox for Automatic Music Transcription

Contact Info

Product

Resources

About