English
Related papers

Related papers: AST: Audio Spectrogram Transformer

200 papers

This paper delves into the challenges and advancements in the field of medical image segmentation, particularly focusing on breast cancer diagnosis. The authors propose a novel Transformer-based segmentation model that addresses the…

Image and Video Processing · Electrical Eng. & Systems 2024-09-20 Weijie He , Runyuan Bao , Yiru Cang , Jianjun Wei , Yang Zhang , Jiacheng Hu

We propose a learnable content adaptive front end for audio signal processing. Before the modern advent of deep learning, we used fixed representation non-learnable front-ends like spectrogram or mel-spectrogram with/without neural…

Sound · Computer Science 2024-12-24 Prateek Verma , Chris Chafe

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-11 Dahan Wang , Xiaobin Rong , Shiruo Sun , Yuxiang Hu , Changbao Zhu , Jing Lu

Convolutional Neural Networks (CNN) have been used in Automatic Speech Recognition (ASR) to learn representations directly from the raw signal instead of hand-crafted acoustic features, providing a richer and lossless input signal. Recent…

Sound · Computer Science 2020-02-12 Paul-Gauthier Noé , Titouan Parcollet , Mohamed Morchid

This paper introduces a novel convolutional neural networks (CNN) framework tailored for end-to-end audio deep learning models, presenting advancements in efficiency and explainability. By benchmarking experiments on three standard speech…

Sound · Computer Science 2024-05-06 Linh Vu , Thu Tran , Wern-Han Lim , Raphael Phan

Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier…

Computation and Language · Computer Science 2017-09-25 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Modern day audio signal classification techniques lack the ability to classify low feature audio signals in the form of spectrographic temporal frequency data representations. Additionally, currently utilized techniques rely on full diverse…

Sound · Computer Science 2024-10-30 Noel Elias

Deep Convolutional Neural Networks (CNNs) have significantly advanced deep learning, driving breakthroughs in computer vision, natural language processing, medical diagnosis, object detection, and speech recognition. Architectural…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Saddam Hussain Khan , Rashid Iqbal

The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits…

Sound · Computer Science 2022-08-26 Raviraj Joshi , Subodh Kumar

The objective of this work is to give patch-size flexibility to Audio Spectrogram Transformers (AST). Recent advancements in ASTs have shown superior performance in various audio-based tasks. However, the performance of standard ASTs…

Sound · Computer Science 2023-07-19 Jiu Feng , Mehmet Hamza Erol , Joon Son Chung , Arda Senocak

Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we explore refocusing model attention…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 Baifeng Shi , Siyu Gai , Trevor Darrell , Xin Wang

Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video…

Computer Vision and Pattern Recognition · Computer Science 2018-03-14 Matthijs Van keirsbilck , Bert Moons , Marian Verhelst

Recent models for image processing are using the Convolutional neural network (CNN) which requires a pixel per pixel analysis of the input image. This method works well. However, it is time-consuming if we have large images. To increase the…

Machine Learning · Computer Science 2019-12-10 Mohamed Karim Belaid

The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale datasets are capable of capturing a diverse set of features, and…

Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks. However, in audio tasks, they are either infeasible to train due to extremely large sequence length of audio waveforms or incur a…

Machine Learning · Computer Science 2022-02-02 Surya Kant Sahu , Sai Mitheran , Juhi Kamdar , Meet Gandhi

The field of machine learning has taken a dramatic twist in recent times, with the rise of the Artificial Neural Network (ANN). These biologically inspired computational models are able to far exceed the performance of previous forms of…

Neural and Evolutionary Computing · Computer Science 2015-12-03 Keiron O'Shea , Ryan Nash

Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tune for the application…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Andre Hryniowski , Alexander Wong

Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Despite recent progress, existing approaches often rely on pretrained encoders, semantic distillation,…

Direct speech-to-text translation (ST) models are usually trained on corpora segmented at sentence level, but at inference time they are commonly fed with audio split by a voice activity detector (VAD). Since VAD segmentation is not…

Computation and Language · Computer Science 2020-08-06 Marco Gaido , Mattia Antonino Di Gangi , Matteo Negri , Mauro Cettolo , Marco Turchi

We investigate the usage of convolutional neural networks (CNNs) for the slot filling task in spoken language understanding. We propose a novel CNN architecture for sequence labeling which takes into account the previous context words with…

Computation and Language · Computer Science 2016-06-27 Ngoc Thang Vu
‹ Prev 1 8 9 10 Next ›