Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond

• URL: http://arxiv.org/abs/2304.05032v1
• Date: Tue, 11 Apr 2023 07:39:16 GMT
• Title: Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond
• Authors: Michael Krause, Christof Wei{\ss}, Meinard M\"uller
• Abstract summary: We show how soft dynamic time warping (SoftDTW) can be used as an alternative to CTC. We show that SoftDTW yields results on par with a state-of-the-art multi-label extension of CTC.
• Score: 0.483420384410068
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many tasks in music information retrieval (MIR) involve weakly aligned data, where exact temporal correspondences are unknown. The connectionist temporal classification (CTC) loss is a standard technique to learn feature representations based on weakly aligned training data. However, CTC is limited to discrete-valued target sequences and can be difficult to extend to multi-label problems. In this article, we show how soft dynamic time warping (SoftDTW), a differentiable variant of classical DTW, can be used as an alternative to CTC. Using multi-pitch estimation as an example scenario, we show that SoftDTW yields results on par with a state-of-the-art multi-label extension of CTC. In addition to being more elegant in terms of its algorithmic formulation, SoftDTW naturally extends to real-valued target sequences.

Related papers

• Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation [62.275143240798236]
  Video semantic segmentation dataset has limited categories per video. Less than 10% of queries could be matched to receive meaningful gradient updates during VSS training. Our method achieves state-of-the-art performance on the latest challenging VSS benchmark VSPW without bells and whistles.
  arXiv  Detail & Related papers  (2023-09-14T20:31:06Z)
• OTW: Optimal Transport Warping for Time Series [75.69837166816501]
  Dynamic Time Warping (DTW) has become the pragmatic choice for measuring distance between time series. It suffers from unavoidable quadratic time complexity when the optimal alignment matrix needs to be computed exactly. We introduce a new metric for time series data based on the Optimal Transport framework, called Optimal Transport Warping (OTW)
  arXiv  Detail & Related papers  (2023-06-01T12:45:00Z)
• Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths [54.53208538517505]
  This paper addresses learning end-to-end models for time series data that include a temporal alignment step via dynamic time warping (DTW) We propose a DTW layer based around bi-level optimisation and deep declarative networks, which we name DecDTW. We show that this property is particularly useful for applications where downstream loss functions are defined on the optimal alignment path itself.
  arXiv  Detail & Related papers  (2023-03-19T21:58:37Z)
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification [53.55504611255664]
  FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task. It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
  arXiv  Detail & Related papers  (2023-02-20T07:46:14Z)
• Approximating DTW with a convolutional neural network on EEG data [9.409281517596396]
  We propose a fast and differentiable approximation of Dynamic Time Wrapping (DTW) We show that our methods achieve at least the same level of accuracy as other DTW main approximations with higher computational efficiency.
  arXiv  Detail & Related papers  (2023-01-30T13:27:47Z)
• LB-SimTSC: An Efficient Similarity-Aware Graph Neural Network for Semi-Supervised Time Series Classification [4.7828959446344275]
  We propose a new efficient semi-supervised time series classification technique, LB-SimTSC, with a new graph construction module. We construct the pairwise distance matrix using LB_Keogh and build a graph for the graph neural network. Results demonstrate that this approach can be up to 104x faster than SimTSC when constructing the graph on large datasets.
  arXiv  Detail & Related papers  (2023-01-12T06:49:55Z)
• Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization [68.49738668084693]
  Self-supervised pre-training recently demonstrates success on large-scale multimodal data. Cross-modality alignment (CMA) is only a weak and noisy supervision. CMA might cause conflicts and biases among modalities.
  arXiv  Detail & Related papers  (2022-11-03T18:12:32Z)
• Towards Similarity-Aware Time-Series Classification [51.2400839966489]
  We study time-series classification (TSC), a fundamental task of time-series data mining. We propose Similarity-Aware Time-Series Classification (SimTSC), a framework that models similarity information with graph neural networks (GNNs)
  arXiv  Detail & Related papers  (2022-01-05T02:14:57Z)
• Time-Series Representation Learning via Temporal and Contextual Contrasting [14.688033556422337]
  We propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC) First, the raw time-series data are transformed into two different yet correlated views by using weak and strong augmentations. Second, we propose a novel temporal contrasting module to learn robust temporal representations by designing a tough cross-view prediction task. Third, to further learn discriminative representations, we propose a contextual contrasting module built upon the contexts from the temporal contrasting module.
  arXiv  Detail & Related papers  (2021-06-26T23:56:31Z)
• TC-DTW: Accelerating Multivariate Dynamic Time Warping Through Triangle Inequality and Point Clustering [6.502892821109196]
  The most popular algorithm used today is still the one developed seventeen years ago. The new solution, named TC-DTW, introduces Triangle Inequality and Point Clustering into the algorithm design. In experiments on DTW-based nearest neighbor finding, the new solution avoids as much as 98% (60% average) DTW distance calculations and yields as much as 25X (7.5X average) speedups.
  arXiv  Detail & Related papers  (2021-01-15T16:38:28Z)

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.