English
Related papers

Related papers: Structural sparsification for Far-field Speaker Re…

200 papers

Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational…

Sound · Computer Science 2022-07-25 Xiaohuai Le , Tong Lei , Kai Chen , Jing Lu

Activation sparsity improves compute efficiency and resource utilization in sparsity-aware neural network accelerators. As the predominant operation in DNNs is multiply-accumulate (MAC) of activations with weights to compute inner products,…

Computer Vision and Pattern Recognition · Computer Science 2021-07-16 Amirreza Yousefzadeh , Manolis Sifalakis

Many modern systems for speaker diarization, such as the recently-developed VBx approach, rely on clustering of DNN speaker embeddings followed by resegmentation. Two problems with this approach are that the DNN is not directly optimized…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-16 Kiran Karra , Alan McCree

The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications. There have been a significant amount of work regarding network…

Machine Learning · Computer Science 2020-11-12 Tianyi Chen , Bo Ji , Yixin Shi , Tianyu Ding , Biyi Fang , Sheng Yi , Xiao Tu

From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets. To navigate the Pareto front of model accuracy vs model size, researchers are…

We propose TF-GridNet, a novel multi-path deep neural network (DNN) operating in the time-frequency (T-F) domain, for monaural talker-independent speaker separation in anechoic conditions. The model stacks several multi-path blocks, each…

As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services. In this paper, we propose…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-04 Yi Xie , Cong Shi , Zhuohang Li , Jian Liu , Yingying Chen , Bo Yuan

While deep neural networks (DNNs) have proven to be efficient for numerous tasks, they come at a high memory and computation cost, thus making them impractical on resource-limited devices. However, these networks are known to contain a…

Neural and Evolutionary Computing · Computer Science 2020-07-21 Anthony Berthelier , Yongzhe Yan , Thierry Chateau , Christophe Blanc , Stefan Duffner , Christophe Garcia

Speech enhancement in ad-hoc microphone arrays is often hindered by the asynchronization of the devices composing the microphone array. Asynchronization comes from sampling time offset and sampling rate offset which inevitably occur when…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-01 Nicolas Furnon , Romain Serizel , Slim Essid , Irina Illina

The state-of-the-art deep neural networks (DNNs) have significant computational and data management requirements. The size of both training data and models continue to increase. Sparsification and pruning methods are shown to be effective…

Machine Learning · Computer Science 2021-04-27 Gunduz Vehbi Demirci , Hakan Ferhatosmanoglu

The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it is hardly used in the…

Machine Learning · Computer Science 2022-03-14 Zhuoran Song , Yihong Xu , Han Li , Naifeng Jing , Xiaoyao Liang , Li Jiang

Contextual sparsity is one of the approaches used to reduce computational complexity in the inference process of large language models (LLMs). Existing techniques for efficient LLM inference acceleration based on contextual sparsity with…

Machine Learning · Computer Science 2026-03-17 Georgii Serbin , Kirill Koshkin , Zhongao Sun , Anastasiya Bistrigova , C. C. Korikov

In multi-speaker applications is common to have pre-computed models from enrolled speakers. Using these models to identify the instances in which these speakers intervene in a recording is the task of speaker tracking. In this paper, we…

Artificial neural networks (ANN) have become the mainstream acoustic modeling technique for large vocabulary automatic speech recognition (ASR). A conventional ANN features a multi-layer architecture that requires massive amounts of…

Neural and Evolutionary Computing · Computer Science 2019-11-20 Jibin Wu , Emre Yilmaz , Malu Zhang , Haizhou Li , Kay Chen Tan

In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-11 Kristina Tesch , Timo Gerkmann

We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple…

Sound · Computer Science 2018-04-27 Sergey Novoselov , Andrey Shulipa , Ivan Kremnev , Alexandr Kozlov , Vadim Shchemelinin

In this paper we propose the Structured Deep Neural Network (Structured DNN) as a structured and deep learning algorithm, learning to find the best structured object (such as a label sequence) given a structured input (such as a vector…

Machine Learning · Computer Science 2015-06-04 Yi-Hsiu Liao , Hung-Yi Lee , Lin-shan Lee

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-18 Yicheng Du , Aditya Arie Nugraha , Kouhei Sekiguchi , Yoshiaki Bando , Mathieu Fontaine , Kazuyoshi Yoshii

Deep neural networks (DNNs) usually demand a large amount of operations for real-time inference. Especially, fully-connected layers contain a large number of weights, thus they usually need many off-chip memory accesses for inference. We…

Computer Vision and Pattern Recognition · Computer Science 2017-07-13 Yoonho Boo , Wonyong Sung

Despite significant efforts over the last few years to build a robust automatic speech recognition (ASR) system for different acoustic settings, the performance of the current state-of-the-art technologies significantly degrades in noisy…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-17 Salar Jafarlou , Soheil Khorram , Vinay Kothapally , John H. L. Hansen