检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Du, Chenpeng Guo, Yiwei Shen, Feiyu Yu, Kai Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9781728163277

In this paper, we describe the systems developed by the SJTU X-LANCE team for LIMMITS 2023 Challenge, and we mainly focus on the winning system on naturalness for track 1. The aim of this challenge is to build a multi-speaker multi-lingual text-to-speech (TTS) system for Marathi, Hindi and Telugu. Each of the languages has a male and a female speaker in the given dataset. In track 1, only 5 hours data from each speaker can be selected to train the TTS model. Our system is based on the recently proposed VQTTS that utilizes VQ acoustic feature rather than mel-spectrogram. We introduce additional speaker embeddings and language embeddings to VQTTS for controlling the speaker and language information. In the cross-lingual evaluations where we need to synthesize speech in a cross-lingual speaker's voice, we provide a native speaker's embedding to the acoustic model and the target speaker's embedding to the vocoder. In the subjective MOS listening test on naturalness, our system achieves 4.77 which ranks first. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Efficient Text-Only Domain Adaptation For CTC-Based ASR

Efficient Text-Only Domain Adaptation For CTC-Based ASR

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Chen, Chang Gong, Xun Qian, Yanmin Ai Institute Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798350306897

For connectionist temporal classification (CTC) based speech recognition (ASR) models, text-only domain adaptation still faces several challenges. In this study, we propose an efficient text-only domain adaptation method for CTC-based models. We introduce the assistant textual adapter (ATA) to learn textual features and transform them into the latent space of the acoustic encoder. With the help of the ATA module, the adaptation is achieved by fine-tuning the top layers of the acoustic encoder with the target domain text. Meanwhile, further improvement can be obtained by the integration with shallow fusion (SF). Adapted from LibriSpeech, experiments show that the proposed method can achieve averaged 29.7% relative WER reduction (WERR) compared with the un-adapted baseline on WSJ, and 10.5% WERR compared to SF as well. Moreover, it also shows 15.4∼37.1% WERR for 10 GigaSpeech target domains test sets compared to the un-adapted baseline, and also 6.5% WERR on average compared with SF. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LLM on Automatic Paper Reviewing Tasks 30

Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LL...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhou, Ruiyang Chen, Lu Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9782493814104

The use of large language models (LLM), especially ChatGPT, to help with research has come into practice. Researchers use it for timely advice and hope to obtain in-depth feedback. However, can LLM be a qualified and reliable reviewer? Although there already exist several review-related datasets, few works have carefully and thoroughly inspected model's capability as a reviewer, especially the correctness of generated reviews. In this paper, we first evaluate GPT-3.5 and GPT-4 (the current top-performing LLM) on 2 types of tasks under different settings: the score prediction task and the review generation task. In addition, we propose a dataset containing 196 review-revision multiple-choice questions (RR-MCQ) with detailed labels from the review-rebuttal forum in ICLR-2023. By asking questions from technical details to the overall presentation and quality, our RR-MCQ data provides a more complete model ability assessment. The results show that LLM is generally helpful, but great caution is needed as it always makes mistakes. Although it can give passable decisions (> 60% accuracy) on single options, completely correct answers are still rare (about 20%);models are still weak on long paper processing, zero-shot scoring, and giving critical feedback like human reviewers. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Joint Channel and Multi-User Detection Empowered with Machine Learning

引用

computers, Materials & Continua 2022年第1期70卷 109-121页

作者： Mohammad Sh.Daoud Areej Fatima Waseem Ahmad Khan Muhammad Adnan Khan Sagheer Abbas Baha Ihnaini Munir Ahmad Muhammad Sheraz Javeid Shabib Aftab College of Engineering Al Ain UniversityAbu Dhabi112612UAE Department of Computer Science Lahore Garrison UniversityLahore54792Pakistan School of Computer Science National College of Business Administration and EconomicsLahore54000Pakistan Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of Software EngineeringGachon UniversitySeongnam13557South Korea Department of Computer Science College of Science and TechnologyWenzhou Kean University325060USA Department of Computer Science Hameeda Rasheed Institute of Science and TechnologyMultan66000Pakistan

The numbers of multimedia applications and their users increase with each passing *** multi-carrier systems have been developed along with varying techniques of space-time coding to address the demand of the future generation of network *** this article,a fuzzy logic empowered adaptive backpropagation neural network(FLeABPNN)algorithm is proposed for joint channel and multi-user detection(CMD).FLeABPNN has two *** first stage estimates the channel parameters,and the second performsmulti-user *** proposed approach capitalizes on a neuro-fuzzy hybrid systemthat combines the competencies of both fuzzy logic and neural *** study analyzes the results of using FLeABPNN based on a multiple-input andmultiple-output(MIMO)receiver with conventional partial oppositemutant particle swarmoptimization(POMPSO),total-OMPSO(TOMPSO),fuzzy logic empowered POMPSO(FL-POMPSO),and FL-TOMPSO-based MIMO *** FLeABPNN-based receiver renders better results than other techniques in terms of minimum mean square error,minimum mean channel error,and bit error rate.

关键词： Channel and multi-user detection minimum mean square error multiple-input and multiple-output minimum mean channel error bit error rate

来源：评论

学校读者我要写书评

暂无评论

To Store or Not? Online Data Selection for Federated Learning with Limited Storage 23

To Store or Not? Online Data Selection for Federated Learnin...

引用

2023 World Wide Web Conference, WWW 2023

作者： Gong, Chen Zheng, Zhenzhe Wu, Fan Shao, Yunfeng Li, Bingshuai Chen, Guihai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Huawei Noah s Ark Lab Beijing China

ISBN: (纸本)9781450394161

Machine learning models have been deployed in mobile networks to deal with massive data from different layers to enable automated network management and intelligence on devices. To overcome high communication cost and severe privacy concerns of centralized machine learning, federated learning (FL) has been proposed to achieve distributed machine learning among networked devices. While the computation and communication limitation has been widely studied, the impact of on-device storage on the performance of FL is still not explored. Without an effective data selection policy to filter the massive streaming data on devices, classical FL can suffer from much longer model training time (4 ×) and significant inference accuracy reduction (7%), observed in our experiments. In this work, we take the first step to consider the online data selection for FL with limited on-device storage. We first define a new data valuation metric for data evaluation and selection in FL with theoretical guarantees for speeding up model convergence and enhancing final model accuracy, simultaneously. We further design ODE, a framework of Online Data sElection for FL, to coordinate networked devices to store valuable data samples. Experimental results on one industrial dataset and three public datasets show the remarkable advantages of ODE over the state-of-the-art approaches. Particularly, on the industrial dataset, ODE achieves as high as 2.5 × speedup of training time and 6% increase in inference accuracy, and is robust to various factors in practical environments. © 2023 ACM.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

FAT-HuBERT: Front-End Adaptive Training of Hidden-Unit BERT For Distortion-Invariant Robust Speech Recognition

FAT-HuBERT: Front-End Adaptive Training of Hidden-Unit BERT ...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Yang, Dongning Wang, Wei Qian, Yanmin Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798350306897

Advancements in monaural speech enhancement (SE) techniques have greatly improved the perceptual quality of speech. However, integrating these techniques into automatic speech recognition (ASR) systems has not yielded the expected performance gains, primarily due to the introduction of distortions during the SE process. In this paper, we propose a novel approach called FAT-HuBERT, which leverages distortion-invariant self-supervised learning (SSL) to enhance the robustness of ASR. To address the distortions introduced by the SE frontends, we introduce layer-wise fusion modules that incorporate features extracted from both observed noisy signals and enhanced signals. During training, the SE frontend is randomly selected from a pool of models. We evaluate the performance of FAT-HuBERT on simulated noisy speech generated from LIBRISPEECH as well as real-world noisy speech from the CHIME-4 1-channel dataset. The experimental results demonstrate a significant relative reduction in word error rate (WER). © 2023 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

A PTAS Framework for Clustering Problems in Doubling Metrics 29th

A PTAS Framework for Clustering Problems in Doubling Metri...

引用

29th International Computing and Combinatorics Conference, COCOON 2023

作者： Wu, Di Xu, Jinhui Wang, Jianxin School of Computer Science and Engineering Central South University Changsha China Xiangjiang Laboratory Changsha410205 China Department of Computer Science and Engineering State University of New York at Buffalo BuffaloNY United States The Hunan Provincial Key Lab of Bioinformatics Central South University Changsha China

ISBN: (纸本)9783031491894

Constrained clustering problems have been studied extensively in recent years. In this paper, we focus on a class of constrained k-median problems with general constraints on facilities, denoted as GCF k-CMedian problems. We present a randomized polynomial-time approximation scheme (PTAS) framework based on the split-tree decomposition and dynamic programming process for GCF k-CMedian problems, such as k-median with service installation costs, k-facility location and priority k-median problems in doubling metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition 48

Front-End Adapter: Adapting Front-End Input of Speech Based ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Chen, Xie Ma, Ziyang Tang, Changli Wang, Yujin Zheng, Zhisheng Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-Lance Lab Department of Computer Science and Engineering Shanghai China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9781728163277

Recent years have witnessed a boom in self-supervised learning (SSL) in various areas including speech processing. Speech based SSL models present promising performance in a range of speech related tasks. However, the training of SSL models is computationally expensive and a common practice is to fine-tune a released SSL model on the specific task. It is essential to use consistent front-end input during pre-training and fine-tuning. This consistency may introduce potential issues when the optimal front-end is not the same as that used in pre-training. In this paper, we propose a simple but effective front-end adapter to address this front-end discrepancy. By minimizing the distance between the outputs of different front-ends, the filterbank feature (Fbank) can be compatible with SSL models which are pre-trained with waveform. The experiment results demonstrate the effectiveness of our proposed front-end adapter on several popular SSL models for the speech recognition task. © 2023 IEEE.

关键词： Adapter Automatic Speech Recognition Front-end Feature Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

X-ray Image-Based COVID-19 Patient Detection Using Machine Learning-Based Techniques

引用

computer Systems science & engineering 2022年第11期43卷 671-682页

作者： Shabana Habib Saleh Alyahya Aizaz Ahmed Muhammad Islam Sheroz Khan Ishrat Khan Muhammad Kamil Department of Information Technology College of ComputerQassim UniversityBuraidah52571Saudi Arabia Department of Electrical Engineering College of Engineering&Information TechnologyOnaizah CollegesOnaizah51911Saudi Arabia Digital Image Processing Lab Islamia CollegePeshawar25120KPKPakistan Department of Computer Science College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Electrical Engineering National University of Computer and Emerging SciencesPeshawarPakistan

In early December 2019,the city of Wuhan,China,reported an outbreak of coronavirus disease(COVID-19),caused by a novel severe acute respiratory syndrome coronavirus-2(SARS-CoV-2).On January 30,2020,the World Health Organization(WHO)declared the outbreak a global pandemic *** the face of the COVID-19 pandemic,the most important step has been the effective diagnosis and monitoring of infected *** COVID-19 using Machine Learning(ML)technologies can help the health care unit through assistive diagnostic suggestions,which can reduce the health unit's burden to a certain *** paper investigates the possibilities of ML techniques in identifying/detecting COVID-19 patients including both conventional and exploring from chest X-ray images the effect of viral *** approach includes preprocessing,feature extraction,and ***,the features are extracted using the Histogram of Oriented(HOG)and Local Binary Pattern(LBP)feature ***,for the extracted features classification,six ML models of Support Vector Machine(SVM)and K-Nearest Neighbor(KNN)is *** results show that the diagnostic accuracy of random forest classifier(RFC)on extracted HOG plusLBP features is as high as 94%followed by SVM at 93%.The sensitivity of the K-nearest neighbour model has reached an accuracy of 88%.Overall,the predicted approach has shown higher classification accuracy and effective diagnostic *** is a highly useful tool for clinical practitioners and radiologists to help them in diagnosing and tracking the cases of COVID-19.

关键词： Image pre-processing detection classification x-ray images filter

来源：评论

学校读者我要写书评

暂无评论

A VARIATIONAL APPROACH TO WEAKLY CONTINUOUS RELATIONS IN BANACH SPACES

引用

SIAM Journal on Optimization 2025年第2期35卷 767-788页

作者： Aussel, Didier Giuli, Massimiliano Milasi, Monica Scopelliti, Domenico Lab. PROMES UPR CNRS 8521 Universit\'e de Perpignan Via Domitia Perpignan France Department of Information Engineering Computer Science and Mathematics University of L'Aquila Italy Department of Economics University of Messina Messina Italy Department of Economics and Management University of Brescia Brescia Italy

Optimization and equilibrium problems have been extensively studied when the involved preference relations admit a representation by means of real-valued functions. Although these problems have been analyzed under very minimal assumptions on the representation function, this context could appear to be quite restrictive in some practical situations. By using tools of variational analysis and normal operator techniques, very recently some authors have explored the properties of preference relations that do not necessarily admit a numerical representation. However, these contributions are limited to finite-dimensional settings. Our aim in the present work is to develop a new analysis of preference relations in topological spaces and to analyze, in Banach spaces, a suitable concept of a normal operator to the upper contour set. As an application of our theoretical developments, we analyze a particular preference equilibrium problem (of which a preference maximization problem is a particular case) by using a suitable quasi-variational inequality formulation;as an example, a preference allocation problem is also considered. Copyright © by SIAM. Unauthorized reproduction of this article is prohibited.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：