Unified Learnable 2D Convolutional Feature Extraction for ASR

• URL: http://arxiv.org/abs/2509.10031v1
• Date: Fri, 12 Sep 2025 07:52:51 GMT
• Title: Unified Learnable 2D Convolutional Feature Extraction for ASR
• Authors: Peter Vieting, Benedikt Hilmes, Ralf Schlüter, Hermann Ney,
• Abstract summary: We show how to reduce the influence of existing techniques to achieve a generic front-end.<n>The resulting 2D convolutional front-end is parameter-efficient and suitable for a scenario with limited computational resources.
• Score: 32.004189826728386
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain heavily influenced by classical methods. While this inductive bias may ease the system design, our work aims to develop a more generic front-end for feature extraction. Furthermore, we seek to unify the front-end architecture contrasting with existing approaches that apply a composition of several layer topologies originating from different sources. The experiments systematically show how to reduce the influence of existing techniques to achieve a generic front-end. The resulting 2D convolutional front-end is parameter-efficient and suitable for a scenario with limited computational resources unlike large models pre-trained on unlabeled audio. The results demonstrate that this generic unified approach is not only feasible but also matches the performance of existing supervised learnable feature extractors.

Related papers

• Self-Ensemble Post Learning for Noisy Domain Generalization [18.4218677759831]
  This paper explores how to make existing methods rework when meeting noise.<n>We find that the latent features inside the model have certain discriminative capabilities.<n>We propose the Self-Ensemble Post Learning approach to diversify features which can be leveraged.
  arXiv  Detail & Related papers  (2025-12-11T17:09:35Z)
• Regularizing Learnable Feature Extraction for Automatic Speech Recognition [46.34929961556797]
  Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition.<n>This work investigates regularization methods for training ASR models with learnable feature extraction front-ends.
  arXiv  Detail & Related papers  (2025-06-11T14:46:14Z)
• Enhancing Fine-Grained Visual Recognition in the Low-Data Regime Through Feature Magnitude Regularization [23.78498670529746]
  We introduce a regularization technique to ensure that the magnitudes of the extracted features are evenly distributed. Despite its apparent simplicity, our approach has demonstrated significant performance improvements across various fine-grained visual recognition datasets.
  arXiv  Detail & Related papers  (2024-09-03T07:32:46Z)
• A Noise and Edge extraction-based dual-branch method for Shallowfake and Deepfake Localization [15.647035299476894]
  We develop a dual-branch model that integrates manually designed feature noise with conventional CNN features. The model is superior in comparison and easily outperforms the existing state-of-the-art (SoTA) models.
  arXiv  Detail & Related papers  (2024-09-02T02:18:34Z)
• Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning [82.29761875805369]
  One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. We propose a novel perspective to use pre-defined class anchors serving as feature centroid to unidirectionally guide feature learning. The proposed Semantic Anchor Regularization (SAR) can be used in a plug-and-play manner in the existing models.
  arXiv  Detail & Related papers  (2023-12-19T05:52:38Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Dynamic Perceiver for Efficient Visual Recognition [87.08210214417309]
  We propose Dynamic Perceiver (Dyn-Perceiver) to decouple the feature extraction procedure and the early classification task. A feature branch serves to extract image features, while a classification branch processes a latent code assigned for classification tasks. Early exits are placed exclusively within the classification branch, thus eliminating the need for linear separability in low-level features.
  arXiv  Detail & Related papers  (2023-06-20T03:00:22Z)
• Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems [61.11799513362704]
  We propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective.
  arXiv  Detail & Related papers  (2023-03-03T02:07:40Z)
• Style Interleaved Learning for Generalizable Person Re-identification [69.03539634477637]
  We propose a novel style interleaved learning (IL) framework for DG ReID training. Unlike conventional learning strategies, IL incorporates two forward propagations and one backward propagation for each iteration. We show that our model consistently outperforms state-of-the-art methods on large-scale benchmarks for DG ReID.
  arXiv  Detail & Related papers  (2022-07-07T07:41:32Z)
• Class-Specific Semantic Reconstruction for Open Set Recognition [101.24781422480406]
  Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes. We propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of auto-encoder (AE) and prototype learning. Results of experiments conducted on multiple datasets show that the proposed method achieves outstanding performance in both close and open set recognition.
  arXiv  Detail & Related papers  (2022-07-05T16:25:34Z)

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.