English
Related papers

Related papers: Multi-scale Octave Convolutions for Robust Speech …

200 papers

Convolutional neural networks (CNNs) with convolutional and pooling operations along the frequency axis have been proposed to attain invariance to frequency shifts of features. However, this is inappropriate with regard to the fact that…

Computation and Language · Computer Science 2016-08-24 Hwaran Lee , Geonmin Kim , Ho-Gyeong Kim , Sang-Hoon Oh , Soo-Young Lee

This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to directly separate speech from multiple microphone recordings,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-12 Jisi Zhang , Catalin Zorila , Rama Doddipatla , Jon Barker

We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time…

Sound · Computer Science 2016-12-09 Naoya Takahashi , Michael Gygli , Beat Pfister , Luc Van Gool

Deep learning has made significant impacts on multi-view stereo systems. State-of-the-art approaches typically involve building a cost volume, followed by multiple 3D convolution operations to recover the input image's pixel-wise depth.…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Zhenpei Yang , Zhile Ren , Qi Shan , Qixing Huang

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-19 Jiamin Xie , John H. L. Hansen

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-06 Jie Wang , Jingbei Li , Xintao Zhao , Zhiyong Wu , Shiyin Kang , Helen Meng

The transformer architecture has catalyzed revolutionary advances in language modeling. However, recent architectural recipes, such as state-space models, have bridged the performance gap. Motivated by this, we examine the benefits of…

Machine Learning · Computer Science 2024-07-09 Mingchen Li , Xuechen Zhang , Yixiao Huang , Samet Oymak

In speaker verification, the extraction of voice representations is mainly based on the Residual Neural Network (ResNet) architecture. ResNet is built upon convolution layers which learn filters to capture local spatial patterns along all…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-14 Mickael Rouvier , Pierre-Michel Bousquet

Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on…

Computation and Language · Computer Science 2020-01-31 Kazuya Kawakami , Luyu Wang , Chris Dyer , Phil Blunsom , Aaron van den Oord

State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-10 Ge Zhu , Fei Jiang , Zhiyao Duan

Recent advances in vision transformers (ViTs) have demonstrated the advantage of global modeling capabilities, prompting widespread integration of large-kernel convolutions for enlarging the effective receptive field (ERF). However, the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Mingshu Zhao , Yi Luo , Yong Ouyang

In this paper, we propose a stacked convolutional and recurrent neural network (CRNN) with a 3D convolutional neural network (CNN) in the first layer for the multichannel sound event detection (SED) task. The 3D CNN enables the network to…

Sound · Computer Science 2018-01-30 Sharath Adavanne , Archontis Politis , Tuomas Virtanen

3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches…

Computer Vision and Pattern Recognition · Computer Science 2019-05-07 Sambit Ghadai , Xian Lee , Aditya Balu , Soumik Sarkar , Adarsh Krishnamurthy

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Xin Zhang , Chen Liu , Degang Yang , Tingting Song , Yichen Ye , Ke Li , Yingze Song

This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Tianyi Lyu , Dian Gu , Peiyuan Chen , Yaoting Jiang , Zhenhong Zhang , Huadong Pang , Li Zhou , Yiping Dong

Convolutions have become essential in state-of-the-art end-to-end Automatic Speech Recognition~(ASR) systems due to their efficient modelling of local context. Notably, its use in Conformers has led to superior performance compared to…

Computation and Language · Computer Science 2024-07-25 Darshan Prabhu , Yifan Peng , Preethi Jyothi , Shinji Watanabe

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Machine Learning · Computer Science 2022-05-09 Sanghyun Yoo , Inchul Song , Yoshua Bengio

Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Yinpeng Chen , Xiyang Dai , Mengchen Liu , Dongdong Chen , Lu Yuan , Zicheng Liu

Conventional Convolutional Neural Networks (CNNs) in the real domain have been widely used for audio classification. However, their convolution operations process multi-channel inputs independently, limiting the ability to capture…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-27 Arshdeep Singh , Vinayak Abrol , Mark D. Plumbley