Polyphonic Note Transcription of Time-Domain Audio Signal with Deep WaveNet Architecture

Martak, Lukas Samuel; Šajgalík, Márius; Benešová, Wanda

doi:10.1109/iwssip.2018.8439708

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This case considers a network derived from WaveNet (Van Den Oord et al [19]) for Polyphonic Note Transcription of Time-Domain Audio Signal ( [42]). It is made of 20 stacked residual blocks composed by a 1 × 1 skip connection and a Dilated Convolutional block of 128 channels each.…”

Section: Wn-pnt Use-casementioning

confidence: 99%

See 1 more Smart Citation

Optimizing Temporal Convolutional Network inference on FPGA-based accelerators

Carreras¹,

Deriu²,

Raffo³

et al. 2020

Preprint

View full text Add to dashboard Cite

Convolutional Neural Networks are extensively used in a wide range of applications, commonly including computer vision tasks like image and video classification, recognition and segmentation. Recent research results demonstrate that multilayer (deep) network involving mono-dimensional convolutions and dilation can be effectively used in time series and sequences classification and segmentation, as well as in tasks involving sequence modelling. These structures, commonly referred to as Temporal Convolutional Networks (TCNs), have been demonstrated to consistently outperform Recurrent Neural Networks in terms of accuracy and training time [1]. While FPGA-based inference accelerators for classic CNNs are widespread, literature is lacking in a quantitative evaluation of their usability on inference for TCN models. In this paper we present such an evaluation, considering a CNN accelerator with specific features supporting TCN kernels as a reference and a set of state-ofthe-art TCNs as benchmark. Experimental results show that, during TCN execution, operational intensity can be critical for the overall performance. We propose a convolution scheduling based on batch processing that can boost efficiency up to 96% of theoretical peak performance. Overall we can achieve up to 111,8 GOPS/s and a power efficiency of 33,9 GOPS/s/W on an Ultrascale+ ZU3EG (up to 10x speedup and 3x power efficiency improvement with respect to pure software implementation).

show abstract

Section: Wn-pnt Use-casementioning

confidence: 99%

“…Fig.17: Efficiency trend and Execution Time on WN-TCN[42] for different batch sizes for NEURAghe 9x10 matrix configuration in ZU3EG…”

mentioning

confidence: 99%

Optimizing Temporal Convolutional Network inference on FPGA-based accelerators

Carreras¹,

Deriu²,

Raffo³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…TCN was examined for tracking the musical beat [4]. Furthermore, Deep WaveNet was introduced for transcribing piano notes directly from raw audio and classifying heart diseases [5], [6]. TasNet was presented for music source separation in time domain.…”

Section: Introductionmentioning

confidence: 99%

IRAWNET: A Method for Transcribing Indonesian Classical Music Notes Directly from Multichannel Raw Audio

Dewi Nurdiyah,

Eko Mulyanto Yuniarno,

Yoyon Kusnendar Suprapto

et al. 2023

EMITTER Int'l J. of Engin. Technol.

View full text Add to dashboard Cite

A challenging task when developing real-time Automatic Music Transcription (AMT) methods is directly leveraging inputs from multichannel raw audio without any handcrafted signal transformation and feature extraction steps. The crucial problems are that raw audio only contains an amplitude in each timestamp, and the signals of the left and right channels have different amplitude intensities and onset times. Thus, this study addressed these issues by proposing the IRawNet method with fused feature layers to merge different amplitude from multichannel raw audio. IRawNet aims to transcribe Indonesian classical music notes. It was validated with the Gamelan music dataset. The Synthetic Minority Oversampling Technique (SMOTE) overcame the class imbalance of the Gamelan music dataset. Under various experimental scenarios, the performance effects of oversampled data, hyperparameters tuning, and fused feature layers are analyzed. Furthermore, the performance of the proposed method was compared with Temporal Convolutional Network (TCN), Deep WaveNet, and the monochannel IRawNet. The results proved that proposed method almost achieves superior results in entire metric performances with 0.871 of accuracy, 0.988 of AUC, 0.927 of precision, 0.896 of recall, and 0.896 of F1 score.

show abstract