检索结果-南通市图书馆

Joint On-Demand Pruning and Online Distillation in automatic speech recognition Language Model Optimization

Computers, Materials & Continua 2023年第12期77卷 2833-2856页

作者： Soonshin Seo Ji-Hwan Kim Clova speech Naver CorporationSeongnam13561Korea Department of Computer Science and Engineering Sogang UniversitySeoul04107Korea

automatic speech recognition(ASR)systems have emerged as indispensable tools across a wide spectrum of applications,ranging from transcription services to voice-activated assistants.To enhance the performance of these systems,it is important to deploy efficient models capable of adapting to diverse deployment conditions.In recent years,on-demand pruning methods have obtained significant attention within the ASR domain due to their adaptability in various deployment scenarios.However,these methods often confront substantial trade-offs,particularly in terms of unstable accuracy when reducing the model size.To address challenges,this study introduces two crucial empirical findings.Firstly,it proposes the incorporation of an online distillation mechanism during on-demand pruning training,which holds the promise of maintaining more consistent accuracy levels.Secondly,it proposes the utilization of the Mogrifier long short-term memory(LSTM)language model(LM),an advanced iteration of the conventional LSTM LM,as an effective alternative for pruning targets within the ASR framework.Through rigorous experimentation on the ASR system,employing the Mogrifier LSTM LM and training it using the suggested joint on-demand pruning and online distillation method,this study provides compelling evidence.The results exhibit that the proposed methods significantly outperform a benchmark model trained solely with on-demand pruning methods.Impressively,the proposed strategic configuration successfully reduces the parameter count by approximately 39%,all the while minimizing trade-offs.

关键词： automatic speech recognition neural language model Mogrifier long short-term memory pruning distillation efficient deployment optimization joint training

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Audio-Text Multimodal speech recognition via Dual-Tower Architecture for Mandarin Air Traffic Control Communications

引用

Computers, Materials & Continua 2024年第3期78卷 3215-3245页

作者： Shuting Ge Jin Ren Yihua Shi Yujun Zhang Shunzhi Yang Jinfeng Yang School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic UniversityShenzhen518055China Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518055China Industrial Training Centre Shenzhen Polytechnic UniversityShenzhen518055China

In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in

关键词： speech-text multimodal automatic speech recognition semantic alignment air traffic control communications dual-tower architecture

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Robust Conformer-Based speech recognition Model for Mandarin Air Traffic Control

引用

Computers, Materials & Continua 2023年第10期77卷 911-940页

作者： Peiyuan Jiang Weijun Pan Jian Zhang Teng Wang Junxiang Huang College of Air Traffic Management Civil Aviation Flight University of ChinaDeyang618307China East China Air Traffic Management Bureau Xiamen Air Traffic Management StationXiamen361015China

This study aims to address the deviation in downstream tasks caused by inaccurate recognition results when applying automatic speech recognition(ASR)technology in the Air Traffic Control(ATC)field.This paper presents a novel cascaded model architecture,namely Conformer-CTC/Attention-T5(CCAT),to build a highly accurate and robust ATC speech recognition model.To tackle the challenges posed by noise and fast speech rate in ATC,the Conformer model is employed to extract robust and discriminative speech representations from raw waveforms.On the decoding side,the Attention mechanism is integrated to facilitate precise alignment between input features and output characters.The Text-To-Text Transfer Transformer(T5)language model is also introduced to handle particular pronunciations and code-mixing issues,providing more accurate and concise textual output for downstream tasks.To enhance the model’s robustness,transfer learning and data augmentation techniques are utilized in the training strategy.The model’s performance is optimized by performing hyperparameter tunings,such as adjusting the number of attention heads,encoder layers,and the weights of the loss function.The experimental results demonstrate the significant contributions of data augmentation,hyperparameter tuning,and error correction models to the overall model performance.On the Our ATC Corpus dataset,the proposed model achieves a Character Error Rate(CER)of 3.44%,representing a 3.64%improvement compared to the baseline model.Moreover,the effectiveness of the proposed model is validated on two publicly available datasets.On the AISHELL-1 dataset,the CCAT model achieves a CER of 3.42%,showcasing a 1.23%improvement over the baseline model.Similarly,on the Librispeech dataset,the CCAT model achieves a Word Error Rate(WER)of 5.27%,demonstrating a performance improvement of 7.67%compared to the baseline model.Additionally,this paper proposes an evaluation criterion for assessing the robustness of ATC speech recognition systems.In robustness evaluation experiments

关键词： Air traffic control automatic speech recognition conformer robustness evaluation T5 error correction model

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

speech recognition via CTC-CNN Model

引用

Computers, Materials & Continua 2023年第9期76卷 3833-3858页

作者： Wen-Tsai Sung Hao-WeiKang Sung-Jung Hsiao Department of Electrical Engineering National Chin-Yi University of TechnologyTaichung411030Taiwan Department of Information Technology Takming University of Science and TechnologyTaipei11451Taiwan

In the speech recognition system,the acoustic model is an important underlying model,and its accuracy directly affects the performance of the entire system.This paper introduces the construction and training process of the acoustic model in detail and studies the Connectionist temporal classification(CTC)algorithm,which plays an important role in the end-to-end framework,established a convolutional neural network(CNN)combined with an acoustic model of Connectionist temporal classification to improve the accuracy of speech recognition.This study uses a sound sensor,ReSpeakerMic Array v2.0.1,to convert the collected speech signals into text or corresponding speech signals to improve communication and reduce noise and hardware interference.The baseline acousticmodel in this study faces challenges such as long training time,high error rate,and a certain degree of overfitting.The model is trained through continuous design and improvement of the relevant parameters of the acousticmodel,and finally the performance is selected according to the evaluation index.Excellentmodel,which reduces the error rate to about 18%,thus improving the accuracy rate.Finally,comparative verificationwas carried out from the selection of acoustic feature parameters,the selection of modeling units,and the speaker’s speech rate,which further verified the excellent performance of the CTCCNN_5+BN+Residual model structure.In terms of experiments,to train and verify the CTC-CNN baseline acoustic model,this study uses THCHS-30 and ST-CMDS speech data sets as training data sets,and after 54 epochs of training,the word error rate of the acoustic model training set is 31%,the word error rate of the test set is stable at about 43%.This experiment also considers the surrounding environmental noise.Under the noise level of 80∼90 dB,the accuracy rate is 88.18%,which is the worst performance among all levels.In contrast,at 40–60 dB,the accuracy was as high as 97.33%due to less noise pollution.

关键词： Artificial intelligence speech recognition speech to text convolutional neural network automatic speech recognition

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Use of AI Voice Authentication Technology Instead of Traditional Keypads in Security Devices

引用

Journal of Computer and Communications 2022年第6期10卷 11-21页

作者： Deepak Ramesh Chandran Iris Energy LLC Edison USA

Traditional keypads and text-based passwords are vulnerable to scams and hacks, leading to enormous levels of embezzlement and frauds apart from various other threats to data security. AI based voice authentication holds unparalleled value for data protection, security, and privacy, by providing an effective alternative to traditional password-based protection. This paper reports the findings of a limited literature review that forms the basis for further research towards enhancing the reliability and security of AI voice authentication. Based on the findings of the review of existing literature, this paper proposes that integration of the blockchain technology with the AI voice authentication can significantly enhance the data security, starting from mobile devices to the security of big agencies and banks. The key processes in implementing an AI voice authentication system are proposed as a conceptual model, to facilitate further research for implementation.

关键词： Artificial Intelligence Voice Authentication Blockchain Data Security automatic speech recognition Voice Biometrics

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Phonetic-Semantic Pre-Training Model for Robust speech recognition

引用

CAAI Artificial Intelligence Research 2022年第1期1卷 1-7页

作者： Xueyang Wu Rongzhong Lian Di Jiang Yuanfeng Song Weiwei Zhao Qian Xu Qiang Yang Department of Computer Science and Engineering The Hong Kong University of Science and TechnologyHong KongChina WeBank Co.Ltd. Shenzhen 518057China

Robustness is a long-standing challenge for automatic speech recognition(ASR)as the applied environment of any ASR system faces much noisier speech samples than clean training corpora.However,it is impractical to annotate every types of noisy environments.In this work,we propose a novel phonetic-semantic pre-training(PSP)framework that allows a model to effectively improve the performance of ASR against practical noisy environments via seamlessly integrating pre-training,self-supervised learning,and fine-tuning.In particular,there are three fundamental stages in PSP.First,pre-train the phone-to-word transducer(PWT)to map the generated phone sequence to the target text using only unpaired text data;second,continue training the PWT on more complex data generated from an empirical phone-perturbation heuristic,in additional to self-supervised signals by recovering the tainted phones;and third,fine-tune the resultant PWT with real world speech data.We perform experiments on two real-life datasets collected from industrial scenarios and synthetic noisy datasets,which show that the PSP effectively improves the traditional ASR pipeline with relative character error rate(CER)reductions of 28.63%and 26.38%,respectively,in two real-life datasets.It also demonstrates its robustness against synthetic highly noisy speech datasets.

关键词： pre-training automatic speech recognition self-supervised learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Securing User Authentication with Server-Side Voice Verification

引用

Journal of Computer and Communications 2023年第5期11卷 137-150页

作者： Deepak R. Chandran Sanath Kumar S. Deepashri Emergence Technologies LLC Willow Grove PA USA Iris Energy LLC Edison NJ USA

User authentication is critical to the security of any information system. The traditional text-based passwords and even biometric systems based on face and fingerprint validation suffer from various drawbacks. Voice-based authentication systems have emerged as an effective alternative method. Within the user authentication systems, the server-side voice authentication systems added advantages. The purpose of this paper is to present an innovative approach to the use of voice verification for user authentication. This paper describes a new framework for the implementation of server-side voice authentication, ensuring that only the users who are authenticated and validated can access the system. In addition to providing enhanced security and a more pleasant user experience, this technology has potential applications in a wide range of fields.

关键词： Voice Authentication Data Security Voice Biometrics automatic speech recognition

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Real Time speech Based Integrated Development Environment for C Program

引用

Circuits and Systems 2016年第3期7卷 69-82页

作者： Bharathi Bhagavathsingh Kavitha Srinivasan Mariappan Natrajan Department of CSE SSN College of Engineering Kalavakkam India

This automatic speech recognition (ASR) is the process which converts an acoustic signal captured by the microphone to written text. The motivation of the paper is to create a speech based Integrated Development Environment (IDE) for C program. This paper proposes a technique to facilitate the visually impaired people or the person with arm injuries with excellent programming skills that can code the C program through voice input. The proposed system accepts the C program as voice input and produces compiled C program as output. The user should utter each line of the C program through voice input. First the voice input is recognized as text. The recognized text will be converted into C program by using syntactic constructs of the C language. After conversion, C program will be fetched as input to the IDE. Furthermore, the IDE commands like open, save, close, compile, run are also given through voice input only. If any error occurs during the compilation process, the error is corrected through voice input only. The errors can be corrected by specifying the line number through voice input. Performance of the speech recognition system is analyzed by varying the vocabulary size as well as number of mixture components in HMM.

关键词： automatic speech recognition Integrated Development Environment Hidden Markov Model Mel Frequency Cepstral Coefficients

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Spectral subtraction in model distance maximizing framework for robust speech recognition

Spectral subtraction in model distance maximizing framework ...

引用

2008 9th International Conference on Signal Processing(ICSP’2008)

作者： Bagher BabaAli Hossein Sameti Mehran Safayani Department of Computer Science Islamic Azad University-Dashtestan BranchBorazjanIran Computer Engineering Department Sharif University of TechnologyTehranIran

This paper has presented a novel discriminative parameters calibration approach based on the Model Distance Maximizing（MDM） to improve the performance of our previous proposed robustness method named spectral subtraction（SS） in likelihoodmaximizing framework.In the previous work,for adjusting the spectral over-subtraction factor of SS,conventional ML approach is used that only utilizes the true model without considering other confused models.This makes it very probably to reach a suboptimal solution.While in MDM,by maximizing the dissimilarities among models,the performance of our speech recognizer-based spectral subtraction method could be further improved.Experimental results based on FarsDat database have demonstrated that MDM approach outperformed ML in term of recognition accuracy.

关键词： Robustness speech recognition speech enhancement Error analysis Filters Calibration Additive noise Signal to noise ratio Decoding automatic speech recognition

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Acoustic Model Compression with Knowledge Transfer

Acoustic Model Compression with Knowledge Transfer

引用

第十四届全国人机语音通讯学术会议

作者： Jiangyan Yi Jianhua Tao Zhengqi Wen Ya Li Hao Ni National Laboratory of Pattern recognition Institute of AutomationChinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology Institute of AutomationChinese Academy of Sciences

Mobile devices have limited computing power and limited memory.Thus,large deep neural network（DNN） based acoustic models are not well suited for application on mobile devices.In order to alleviate this problem,this paper proposes to compress acoustic models by using knowledge transfer.This approach forces a large teacher model to transfer generalized knowledge to a small student model.The student model is trained with a linear interpolation of hard probabilities and soft probabilities to learn generalized knowledge from the teacher model.The hard probabilities are generated from a Gaussian mixture model hidden Markov model（GMM-HMM） system.The soft probabilities are computed from a teacher model（DNN or RNN）.Experiments on AMI corpus show that a small student model obtains 2.4%relative WER improvement over a large teacher model with almost 7.6 times compression ratio.

关键词： model compression knowledge transfer deep neural networks automatic speech recognition

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：