检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Kazuki Irie Shankar Kumar Michael Nirschl Hank Liao Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen Germany Google Inc. New York NY 10011 USA

ISBN: (纸本)9781538646595

We present a new architecture and a training strategy for an adaptive mixture of experts with applications to domain robust language modeling. The proposed model is designed to benefit from the scenario where the training data are available in diverse domains as is the case for YouTube speech recognition. The two core components of our model are an ensemble of parallel long short-term memory (LSTM) expert layers for each domain and another LSTM based network which generates state dependent mixture weights for combining expert LSTM states by linear interpolation. The resulting model is a recurrent adaptive mixture model (RADMM) of domain experts. We train our model on 4.4B words from YouTube speech recognition data. We report results on the YouTube speech recognition test set. Compared with a background LSTM model, we obtain up to 12% relative improvement in perplexity and an improvement in word error rate from 12.3% to 12.1% while using a lattice rescoring with strong pruning.

关键词： language modeling neural networks speech recognition mixture of experts domain adaptation modelling languages Speech recognition Neural network Professional personnel YouTube Mixture models training policy new buildings

来源：评论

学校读者我要写书评

暂无评论

Confidence scores for acoustic model adaptation

Confidence scores for acoustic model adaptation

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Christian Gollan Michiel Bacchiani Human Language Technology and Pattern Recognition Computer Science Department 6 RWTH Aachen University Germany Google Inc. New York NY USA

This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. We show that adaptation approaches with a limited number of free parameters such as linear transform-based approaches are robust in the face of frame labeling errors whereas adaptation approaches with a large number of free parameters such as MAP are sensitive to the quality of the supervision and hence benefit most from use of confidences. Different approaches for using confidence information in adaptation are investigated. This analysis shows that a thresholding approach is effective in that it improves the frame labeling accuracy with little detrimental effect on frame recall. Experimental results show an absolute WER reduction of 2.1% over a CMLLR adapted system on a video transcription task.

关键词： Adaptation model Maximum likelihood linear regression Parameter estimation Speech Robustness Labeling Multimedia systems humans pattern recognition computer science

来源：评论

学校读者我要写书评

暂无评论

ROBUST KNOWLEDGE DISTILLATION FROM RNN-T MODELS WITH NOISY TRAINING LABELS USING FULL-SUM LOSS

arXiv

引用

arXiv 2023年

作者： Zeineldeen, Mohammad Audhkhasi, Kartik Baskar, Murali Karthick Ramabhadran, Bhuvana Human Language Technology and Pattern Recognition Computer Science Department Rwth Aachen University Aachen52074 Germany Google Llc New York United States

This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNNT) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech to train a student model. Soft distillation is another popular KD method that distills the output logits of the teacher model. Due to the nature of RNN-T alignments, applying soft distillation between RNNT architectures having different posterior distributions is challenging. In addition, bad teachers having high word-error-rate (WER) reduce the efficacy of KD. We investigate how to effectively distill knowledge from variable quality ASR teachers, which has not been studied before to the best of our knowledge. We show that a sequence-level KD, full-sum distillation, outperforms other distillation methods for RNN-T models, especially for bad teachers. We also propose a variant of full-sum distillation that distills the sequence discriminative knowledge of the teacher leading to further improvement in WER. We conduct experiments on public datasets namely SpeechStew and LibriSpeech, and on in-house production data. Copyright © 2023, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Theoretical Review: Risk Mitigation Through Trusted human Framework for Insider Threats

A Theoretical Review: Risk Mitigation Through Trusted Human ...

引用

2019 International Conference on Cybersecurity, ICoCSec 2019

作者： Apau, Mohd Nazer Sedek, Muliati Ahmad, Rabiah Information Security and Network Research Group Center for Advanced Computing Technology Faculty of Information and Communication Technology Universiti Teknikal Malaysia Melaka Department of Computer Science Department of Language and Human Development Durian Tunggal Melaka76109 Malaysia

ISBN: (纸本)9781728156576

This paper discusses the possible effort to mitigate insider threats risk and aim to inspire organizations to consider identifying insider threats as one of the risks in the company's enterprise risk management activities. The paper suggests Trusted human Framework (THF) as the on-going and cyclic process to detect and deter potential employees who bound to become the fraudster or perpetrator violating the access and trust given. The mitigation's control statements were derived from the recommended practices in the 'Common Sense Guide to Mitigating Insider Threats' produced by the Software Engineering Institute, Carnegie Mellon University (SEI-CMU). The statements validated via a survey which was responded by fifty respondents who work in Malaysia. © 2019 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Adding semantics to data-driven paraphrasing 53

Adding semantics to data-driven paraphrasing

引用

53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural language Processing of the Asian Federation of Natural language Processing, ACL-IJCNLP 2015

作者： Pavlick, Ellie Bos, Johan Nissim, Malvina Beller, Charley Durme, Benjamin Van Callison-Burch, Chris Computer and Information Science Department University of Pennsylvania United States Center for Language and Cognition Groningen University of Groningen Netherlands Human Language Technology Center of Excellence Johns Hopkins University United States IBM Watson Group United States

ISBN: (纸本)9781941643723

We add an interpretable semantics to the paraphrase database (PPDB). To date, the relationship between phrase pairs in the database has been weakly defined as approximately equivalent. We show that these pairs represent a variety of relations, including directed entailment (little girl/girl) and exclusion (nobody/ someone). We automatically assign semantic entailment relations to entries in PPDB using features derived from past work on discovering inference rules from text and semantic taxonomy induction. We demonstrate that our model assigns these relations with high accuracy. In a downstream RTE task, our labels rival relations from WordNet and improve the coverage of a proof-based RTE system by 17%. © 2015 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Non-stationary feature extraction for automatic speech recognition

Non-stationary feature extraction for automatic speech recog...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zoltán Tüske Pavel Golik Ralf Schlüter Friedhelm R. Drepper Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany Zentralinstitut für Elektronik Forschungszentrum Jülich (KFA) Julich Germany

In current speech recognition systems mainly Short-Time Fourier Transform based features like MFCC are applied. Dropping the short-time stationarity assumption of the voiced speech, this paper introduces the non-stationary signal analysis into the ASR framework. We present new acoustic features extracted by a pitch-adaptive Gammatone filter bank. The noise robustness was proved on AURORA 2 and 4 tasks, where the proposed features outperform the standard MFCC. Furthermore, successful combination experiments via ROVER indicate the differences between the new features and MFCC.

关键词： Mel frequency cepstral coefficient Harmonic analysis Feature extraction Speech Speech recognition Time frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

arXiv

引用

arXiv 2022年

作者： Daheim, Nico Thulke, David Dugast, Christian Ney, Hermann Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany Human Language Technology and Pattern Recognition RWTH Aachen University Germany AppTek GmbH Germany

In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes' theorem. One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document based on the dialog context and generated response. We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets. Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model. Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output. Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements. © 2022, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Editorial: Knowledge engineering, semantics, and signal processing in audio - visual information retrieval

引用

IEEE Transactions on Circuits and Systems for Video technology 2007年第3期17卷 257-258页

作者： Izquierdo, Ebroul Zhang, Jian Sikora, Thomas Huang, Thomas S. Department of Electrical Engineering Queen Mary University of London London El 4NS United Kingdom Sydney Australia School of Computer Science and Engineering University of New South Wales Australia Communication Systems Group Technical University Berlin Berlin Germany ITG University of Illinois at Urbana-Champaign United States Department of Electrical and Computer Engineering Coordinated Science Laboratory United States Image Formation and Processing Group Beckman Institute for Advanced Science and Technology United States Institute's Major Research Theme Human Computer Intelligent Interaction National Academy of Engineering Chinese Academies of Engineering and Sciences China International Association of Pattern Recognition Optical Society of American United States

No abstract available

关键词： Special issues and sections Knowledge engineering Information retrieval Audio-visual systems

来源：评论

学校读者我要写书评

暂无评论

Self-attention transfer networks for speech emotion recognition

引用

Virtual Reality & Intelligent Hardware 2021年第1期3卷 43-54页

作者： Ziping ZHAO Keru Wang Zhongtian BAO Zixing ZHANG Nicholas CUMMINS Shihuang SUN Haishuai WANG Jianhua TAO Björn WSCHULLER College of Computer and Information Engineering Tianjin Normal UniversityTianjin 300387China GLAM-Group on Language Audio&MusicImperial College LondonSW72AZUK Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg86159Germany Department of Biostatistics and Health Informatics IoPPNKing's College LondonLondonSE58AFUK Department of Computer Science and Engineering Fairfield University 06824USA National Laboratory of Pattern Recognition CASIABeijing 100190China

Background A crucial element of human-machine interaction,the automatic detection of emotional states from human speech has long been regarded as a challenging task for machine learning *** vital challenge in speech emotion recognition(SER)is learning robust and discriminative representations from *** machine learning methods have been widely applied in SER research,the inadequate amount of available annotated data has become a bottleneck impeding the extended application of such techniques(e.g.,deep neural networks).To address this issue,we present a deep learning method that combines knowledge transfer and self-attention for SER ***,we apply the log-Mel spectrogram with deltas and delta-deltas as ***,given that emotions are time dependent,we apply temporal convolutional neural networks to model the variations in *** further introduce an attention transfer mechanism,which is based on a self-attention algorithm to learn long-term *** self-attention transfer network(SATN)in our proposed approach takes advantage of attention transfer to learn attention from speech recognition,followed by transferring this knowledge into *** evaluation built on Interactive Emotional Dyadic Motion Capture(IEMOCAP)dataset demonstrates the effectiveness of the proposed model.

关键词： Speech emotion recognition Attention transfer Self-attention Temporal convolutional neural networks(TCNs)

来源：评论

学校读者我要写书评

暂无评论

Communication via eye blinks and eyebrow raises: Video-based human-computer interfaces

引用

Universal Access in the Information Society 2003年第4期2卷 359-373页

作者： Grauman, K. Betke, M. Lombardi, J. Gips, J. Bradski, G.R. Vision Interface Group AI Laboratory Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Computer Science Department Boston University 111 Cummington St BostonMA02215 United States EagleEyes Computer Science Department Boston College Fulton Hall Chestnut HillMA02467 United States Vision Graphics and Pattern Recognition Microcomputer Research Laboratory Intel Corporation SC12-303 2200 Mission College Blvd Santa ClaraCA95054-1537 United States

Two video-based human-computer interaction tools are introduced that can activate a binary switch and issue a selection command. "BlinkLink," as the first tool is called, automatically detects a user's eye blinks and accurately measures their durations. The system is intended to provide an alternate input modality to allow people with severe disabilities to access a computer. Voluntary long blinks trigger mouse clicks, while involuntary short blinks are ignored. The system enables communication using "blink patterns:" sequences of long and short blinks which are interpreted as semiotic messages. The second tool, "EyebrowClicker," automatically detects when a user raises his or her eyebrows and then triggers a mouse click. Both systems can initialize themselves, track the eyes at frame rate, and recover in the event of errors. No special lighting is required. The systems have been tested with interactive games and a spelling program. Results demonstrate overall detection accuracy of 95.6% for BlinkLink and 89.0% for EyebrowClicker. © Springer-Verlag 2003.

关键词： computer vision

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：