English
Related papers

Related papers: Scaling strategies for on-device low-complexity so…

200 papers

Recent research on the time-domain audio separation networks (TasNets) has brought great success to speech separation. Nevertheless, conventional TasNets struggle to satisfy the memory and latency constraints in industrial applications. In…

Audio and Speech Processing · Electrical Eng. & Systems 2021-01-14 Max W. Y. Lam , Jun Wang , Dan Su , Dong Yu

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Wenyong Huang , Wenchao Hu , Yu Ting Yeung , Xiao Chen

Recent speech enhancement models have shown impressive performance gains by scaling up model complexity and training data. However, the impact of dataset variability (e.g. text, language, speaker, and noise) has been underexplored.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-20 Leying Zhang , Wangyou Zhang , Chenda Li , Yanmin Qian

We present a work on low-complexity acoustic scene classification (ASC) with multiple devices, namely the subtask A of Task 1 of the DCASE2021 challenge. This subtask focuses on classifying audio samples of multiple devices with a…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-06 Yanxiong Li , Wenchang Cao , Wei Xie , Qisheng Huang , Wenfeng Pang , Qianhua He

The goal of speech separation is to extract multiple speech sources from a single microphone recording. Recently, with the advancement of deep learning and availability of large datasets, speech separation has been formulated as a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-17 Midia Yousefi , John H. L. Hansen

Time-domain audio separation network (TasNet) has achieved remarkable performance in blind source separation (BSS). Classic multi-channel speech processing framework employs signal estimation and beamforming. For example, Beam-TasNet links…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-13 Hangting Chen , Yang Yi , Dang Feng , Pengyuan Zhang

In this paper, we present Reshape Dimensions Network (ReDimNet), a novel neural network architecture for extracting utterance-level speaker representations. Our approach leverages dimensionality reshaping of 2D feature maps to 1D signal…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-26 Ivan Yakovlev , Rostislav Makarov , Andrei Balykin , Pavel Malov , Anton Okhotnikov , Nikita Torgashov

This paper targets a new scenario that integrates speech separation with speech compression, aiming to disentangle multiple speakers while producing discrete representations for efficient transmission or storage, with applications in online…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-21 Hui-Peng Du , Yang Ai , Xiao-Hang Jiang , Rui-Chen Zheng , Zhen-Hua Ling

This paper proposes a neural network based speech separation method using spatially distributed microphones. Unlike with traditional microphone array settings, neither the number of microphones nor their spatial arrangement is known in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Dongmei Wang , Zhuo Chen , Takuya Yoshioka

Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Huijie Zhang , Yifu Lu , Ismail Alkhouri , Saiprasad Ravishankar , Dogyoon Song , Qing Qu

In this paper, we investigate distillation and pruning methods to reduce model size for non-intrusive speech quality assessment based on self-supervised representations. Our experiments build on XLS-R-SQA, a speech quality assessment model…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-11 Benjamin Stahl , Hannes Gamper

Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks.…

Sound · Computer Science 2020-10-20 João Antônio Chagas Nunes , David Macêdo , Cleber Zanchettin

The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The…

Sound · Computer Science 2019-05-29 Rongzhi Gu , Jian Wu , Shi-Xiong Zhang , Lianwu Chen , Yong Xu , Meng Yu , Dan Su , Yuexian Zou , Dong Yu

Compressing resource-intensive large language models by removing whole transformer blocks is a seemingly simple idea, but identifying which blocks to remove constitutes an exponentially difficult combinatorial problem. In this paper, we…

Machine Learning · Computer Science 2026-02-03 David Jansen , Roman Rausch , David Montero , Roman Orus

Extracting the speech of a target speaker from mixed audios, based on a reference speech from the target speaker, is a challenging yet powerful technology in speech processing. Recent studies of speaker-independent speech separation, such…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Zining Zhang , Bingsheng He , Zhenjie Zhang

This paper introduces an area-based source separation method designed for virtual meeting scenarios. The aim is to preserve speech signals from an unspecified number of sources within a defined spatial area in front of a linear microphone…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-20 Martin Strauss , Okan Köpüklü

Factors that limit the size of the input and output of a neural network include memory requirements for the network states/activations to compute gradients, as well as memory for the convolutional kernels or other weights. The memory…

Computer Vision and Pattern Recognition · Computer Science 2019-12-30 Bas Peters , Eldad Haber , Keegan Lensink

Quantization-Aware Training from scratch has emerged as a promising approach for building efficient large language models (LLMs) with extremely low-bit weights (sub 2-bit), which can offer substantial advantages for edge deployment.…

Machine Learning · Computer Science 2026-02-27 Wenzheng Zhang , Bingzheng Liu , Yang Hu , Xiaoying Bai , Wentao Zhang , Bin Cui

Recently, deep clustering (DPCL) based speaker-independent speech separation has drawn much attention, since it needs little speaker prior information. However, it still has much room of improvement, particularly in reverberant…

Sound · Computer Science 2019-10-25 Ziye Yang , Xiao-Lei Zhang

In multi-speaker scenarios, leveraging spatial features is essential for enhancing target speech. While with limited microphone arrays, developing a compact multi-channel speech enhancement system remains challenging, especially in…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-31 Wen Wen , Qiang Zhou , Yu Xi , Haoyu Li , Ziqi Gong , Kai Yu