Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training

• URL: http://arxiv.org/abs/2010.03749v1
• Date: Thu, 8 Oct 2020 03:47:25 GMT
• Title: Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training
• Authors: Ryoto Ishizuka, Ryo Nishikimi, Eita Nakamura, Kazuyoshi Yoshii
• Abstract summary: This paper describes a neural drum transcription method that detects from music signals the onset times of drums at the $textittatum$ level.
• Score: 20.69310034107256
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper describes a neural drum transcription method that detects from music signals the onset times of drums at the $\textit{tatum}$ level, where tatum times are assumed to be estimated in advance. In conventional studies on drum transcription, deep neural networks (DNNs) have often been used to take a music spectrogram as input and estimate the onset times of drums at the $\textit{frame}$ level. The major problem with such frame-to-frame DNNs, however, is that the estimated onset times do not often conform with the typical tatum-level patterns appearing in symbolic drum scores because the long-term musically meaningful structures of those patterns are difficult to learn at the frame level. To solve this problem, we propose a regularized training method for a frame-to-tatum DNN. In the proposed method, a tatum-level probabilistic language model (gated recurrent unit (GRU) network or repetition-aware bi-gram model) is trained from an extensive collection of drum scores. Given that the musical naturalness of tatum-level onset times can be evaluated by the language model, the frame-to-tatum DNN is trained with a regularizer based on the pretrained language model. The experimental results demonstrate the effectiveness of the proposed regularized training method.

Related papers

• Interpreting learned search: finding a transition model and value function in an RNN that plays Sokoban [3.274397973865673]
  We partially reverse-engineer a convolutional recurrent neural network (RNN) trained to play the puzzle game Sokoban.<n>Prior work found that this network solves more levels with more test-time compute.
  arXiv  Detail & Related papers  (2025-06-11T19:36:17Z)
• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  Formal language theory pertains specifically to recognizers. It is common to instead use proxy tasks that are similar in only an informal sense. We correct this mismatch by training and evaluating neural networks directly as binary classifiers of strings.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [56.092059713922744]
  We show that using high-level contextualized features as prediction targets can achieve superior performance. Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework. Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2024-01-01T12:08:35Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Dynamic Scheduled Sampling with Imitation Loss for Neural Text Generation [10.306522595622651]
  We introduce Dynamic Scheduled Sampling with Imitation Loss (DySI), which maintains the schedule based solely on the training time accuracy. DySI achieves notable improvements on standard machine translation benchmarks, and significantly improves the robustness of other text generation models.
  arXiv  Detail & Related papers  (2023-01-31T16:41:06Z)
• Quark: Controllable Text Generation with Reinforced Unlearning [68.07749519374089]
  Large-scale language models often learn behaviors that are misaligned with user expectations. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods.
  arXiv  Detail & Related papers  (2022-05-26T21:11:51Z)
• Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics [85.31710759801705]
  Current practice requires expensive computational costs in model training for performance prediction. We propose a novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training. Our framework is built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections.
  arXiv  Detail & Related papers  (2022-01-11T20:53:15Z)
• Self-Normalized Importance Sampling for Neural Language Modeling [97.96857871187052]
  In this work, we propose self-normalized importance sampling. Compared to our previous work, the criteria considered in this work are self-normalized and there is no need to further conduct a correction step. We show that our proposed self-normalized importance sampling is competitive in both research-oriented and production-oriented automatic speech recognition tasks.
  arXiv  Detail & Related papers  (2021-11-11T16:57:53Z)
• Exploring Unsupervised Pretraining Objectives for Machine Translation [99.5441395624651]
  Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT) Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence architectures, by masking parts of the input and reconstructing them in the decoder. We compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context.
  arXiv  Detail & Related papers  (2021-06-10T10:18:23Z)
• Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms [18.5148472561169]
  This paper describes an automatic drum transcription (ADT) method that directly estimates a tatum-level drum score from a music signal. To capture the global repetitive structure of drum scores, we introduce a self-attention mechanism with tatum-synchronous positional encoding into the decoder. Experimental results showed that the proposed regularized model outperformed the conventional RNN-based model in terms of the tatum-level error rate and the frame-level F-measure.
  arXiv  Detail & Related papers  (2021-05-12T17:04:16Z)
• Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure [0.0]
  We propose a conditional melody generation model based on a hierarchical recurrent neural network. This model generates melodies with long-term structures based on given chord accompaniments. Results from our listening test indicate that CM-HRNN outperforms AttentionRNN in terms of long-term structure and overall rating.
  arXiv  Detail & Related papers  (2021-02-19T08:22:26Z)
• On Long-Tailed Phenomena in Neural Machine Translation [50.65273145888896]
  State-of-the-art Neural Machine Translation (NMT) models struggle with generating low-frequency tokens. We propose a new loss function, the Anti-Focal loss, to better adapt model training to the structural dependencies of conditional text generation. We show the efficacy of the proposed technique on a number of Machine Translation (MT) datasets, demonstrating that it leads to significant gains over cross-entropy.
  arXiv  Detail & Related papers  (2020-10-10T07:00:57Z)
• Recurrent babbling: evaluating the acquisition of grammar from limited input data [0.30458514384586405]
  Recurrent Neural Networks (RNNs) have been shown to capture various aspects of syntax from raw linguistic input. This paper remedies this state of affairs by training a Long Short-Term Memory network (LSTM) over a realistically sized subset of child-directed input.
  arXiv  Detail & Related papers  (2020-10-09T15:30:05Z)
• Echo State Neural Machine Translation [7.496705711191467]
  We present neural machine translation (NMT) models inspired by echo state network (ESN), named Echo State NMT (ESNMT) We show that even with this extremely simple model construction and training procedure, ESNMT can already reach 70-80% quality of fully trainable baselines.
  arXiv  Detail & Related papers  (2020-02-27T00:08:45Z)

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.