检索结果-内蒙古大学图书馆

attention-based encoder-decoder End-to-End Neural Diarization With Embedding Enhancer

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2024年 32卷 1636-1649页

作者： Chen, Zhengyang Han, Bing Wang, Shuai Qian, Yanmin Shanghai Jiao Tong Univ Dept Comp Sci & Engn Auditory Cognit & Computat Acoust Lab Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China Chinese Univ Hong Kong Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For evaluation, we propose an iterative decoding method that outputs diarization results for each speaker sequentially. Additionally, we propose an Enhancer module to enhance the frame-level speaker embeddings, enabling the model to handle scenarios with an unseen number of speakers. We also explore replacing the transformer encoder with a Conformer architecture, which better models local information. Furthermore, we discovered that commonly used simulation datasets for speaker diarization have a much higher overlap ratio compared to real data. We found that using simulated training data that is more consistent with real data can achieve an improvement in consistency. Extensive experimental validation demonstrates the effectiveness of our proposed methodologies. Our best system achieved a new state-of-the-art diarization error rate (DER) performance on all the CALLHOME(10.08%), DIHARD II (24.64%), and AMI(13.00%) evaluation benchmarks when overlap is considered and no oracle voice activity detection (VAD) is used. Beyond speaker diarization, our AED-EEND system also shows remarkable competitiveness as a speech type detection model.

关键词： Neural speaker diarization attention-based encoder-decoder CALLHOME AMI DIHARD iterative decoding

来源：评论

学校读者我要写书评

暂无评论

HYBRID attention-based encoder-decoder MODEL FOR EFFICIENT LANGUAGE MODEL ADAPTATION

HYBRID ATTENTION-BASED ENCODER-DECODER MODEL FOR EFFICIENT L...

引用

2024 Spoken Language Technology Workshop

作者： Ling, Shaoshi Ye, Guoli Zhao, Rui Gong, Yifan Microsoft Cloud & AI Redmond WA 98052 USA

ISBN: (纸本)9798350392265;9798350392258

The attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years. However, the joint optimization of acoustic model and language model in end-to-end manner has created challenges for text adaptation. In particular, effective, quick and inexpensive adaptation with text input has become a primary concern for deploying AED systems in the industry. To address this issue, we propose a novel model, the hybrid attention-based encoder-decoder (HAED) speech recognition model that preserves the modularity of conventional hybrid automatic speech recognition systems. Our HAED model separates the acoustic and language models, allowing for the use of conventional text-based language model adaptation techniques. We demonstrate that the proposed HAED model yields 23% relative Word Error Rate (WER) improvements when out-of-domain text data is used for language model adaptation, with only a minor degradation in WER on a general test set compared with the conventional AED model.

关键词： speech recognition attention-based encoder-decoder language modeling text adaptation

来源：评论

学校读者我要写书评

暂无评论

Investigating Methods to Improve Language Model Integration for attention-based encoder-decoder ASR Models 22

Investigating Methods to Improve Language Model Integration ...

引用

Interspeech Conference

作者： Zeineldeen, Mohammad Glushko, Aleksandr Michel, Wilfried Zeyer, Albert Schlueter, Ralf Ney, Hermann Rhein Westfal TH Aachen Comp Sci Dept Human Language Technol & Pattern Recognit D-52074 Aachen Germany AppTek GmbH D-52062 Aachen Germany

ISBN: (纸本)9781713836902

attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions. The integration with an external LM trained on much more unpaired text usually leads to better performance. A Bayesian interpretation as in the hybrid autoregressive transducer (HAT) suggests dividing by the prior of the discriminative acoustic model, which corresponds to this implicit LM, similarly as in the hybrid hidden Markov model approach. The implicit LM cannot be calculated efficiently in general and it is yet unclear what are the best methods to estimate it. In this work, we compare different approaches from the literature and propose several novel methods to estimate the ILM directly from the AED model. Our proposed methods outperform all previous approaches. We also investigate other methods to suppress the ILM mainly by decreasing the capacity of the AED model, limiting the label context, and also by training the AED model together with a pre-existing LM.

关键词： speech recognition language model integration attention-based encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Enhancing E-commerce recommendations with sentiment analysis using MLA-EDTCNet and collaborative filtering

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-16页

作者： Krishna, E. S. Phalguna Ramu, T. Bhargava Chaitanya, R. Krishna Ram, M. Sitha Balayesu, Narasimhula Gandikota, Hari Prasad Jagadesh, B. N. GITAM Univ GITAM Sch Technol Dept Comp Sci & Engn Bengaluru Campus Bengaluru India MLR Inst Technol Dept Elect & Elect Engn Hyderabad 500043 Telangana India SRKR Engn Coll Dept ECE Bhimavaram India SRM Univ Sch Engn & Sci Dept Comp Sci & Engn Amaravati Andhra Pradesh India Vasireddy Venkatadri Inst Technol Dept Comp Sci & Engn AIML Guntur India Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Hyderabad 500075 Telangana India VIT AP Univ Sch Comp Sci & Engn Vijayawada 522237 India

The rapid growth of e-commerce has made product recommendation systems essential for enhancing customer experience and driving business success. This research proposes an advanced recommendation framework that integrates sentiment analysis (SA) and collaborative filtering (CF) to improve recommendation accuracy and user satisfaction. The methodology involves feature-level sentiment analysis with a multi-step pipeline: data preprocessing, feature extraction using a log-term frequency-based modified inverse class frequency (LFMI) algorithm, and sentiment classification using a Multi-Layer attention-based encoder-decoder Temporal Convolution Neural Network (MLA-EDTCNet). To address class imbalance issues, a Modified Conditional Generative Adversarial Network (MCGAN) generates balanced oversamples. Furthermore, the Ocotillo Optimization Algorithm (OcOA) fine-tunes the model parameters to ensure optimal performance by balancing exploration and exploitation during training. The integrated system predicts sentiment polarity-positive, negative, or neutral-and combines these insights with CF to provide personalized product recommendations. Extensive experiments conducted on an Amazon product dataset demonstrate that the proposed approach outperforms state-of-the-art models in accuracy, precision, recall, F1-score, and AUC. By leveraging SA and CF, the framework delivers recommendations tailored to user preferences while enhancing engagement and satisfaction. This research highlights the potential of hybrid deep learning techniques to address critical challenges in recommendation systems, including class imbalance and feature extraction, offering a robust solution for modern e-commerce platforms.

关键词： Sentiment analysis Modified conditional generative adversarial network Modified inverse class frequency algorithm Ocotillo optimization algorithm attention-based encoder-decoder Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Joint Beam Search Integrating CTC, attention, and Transducer decoders

引用

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2025年 33卷 598-612页

作者： Sudo, Yui Shakeel, Muhammad Fukumoto, Yosuke Yan, Brian Shi, Jiatong Peng, Yifan Watanabe, Shinji Honda Res Inst Japan Co Ltd Res Div Wako Saitama 3510188 Japan Carnegie Mellon Univ Language Technol Inst Pittsburgh PA 15213 USA Carnegie Mellon Univ Dept Elect & Comp Engn Pittsburgh PA 15213 USA

End-to-end automatic speech recognition (E2E-ASR) can be classified by its decoder architectures, such as connectionist temporal classification (CTC), recurrent neural network transducer (RNN-T), attention-based encoder-decoder, and Mask-CTC models. Each decoder architecture has advantages and disadvantages, leading practitioners to switch between these different models depending on application requirements. Instead of building separate models, we propose a joint modeling scheme where four decoders (CTC, RNN-T, attention, and Mask-CTC) share the same encoder - we refer to this as 4D modeling. The 4D model is trained jointly, which will bring model regularization and maximize the model robustness thanks to their complementary properties. To efficiently train the 4D model, we introduce a two-stage training strategy that stabilizes the joint training. In addition, we propose three novel joint beam search algorithms by combining three decoders (CTC, RNN-T, and attention) to further improve performance. These three beam search algorithms differ in which decoder is used as the primary decoder. We carefully evaluate the performance and computational tradeoffs associated with each algorithm. Experimental results demonstrate that the jointly trained 4D model outperforms the E2E-ASR models trained with only one individual decoder. Furthermore, we demonstrate that the proposed joint beam search algorithm outperforms the previously proposed CTC/attention decoding.

关键词： Decoding Hidden Markov models Computational modeling Training Computational efficiency Transducers Inference algorithms Accuracy Vectors Translation attention-based encoder-decoder beam search CTC RNN-T speech recognition

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Transformer-based Automatic Speech Recognition for Qur’an Reciters

引用

Computers, Materials & Continua 2023年第2期74卷 3471-3487页

作者： Mohammed Hadwan Hamzah A.Alsayadi Salah AL-Hagree Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science College of Applied SciencesTaiz UniversityTaiz6803Yemen Computer Science Department Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Science Department Faculty of SciencesIbb UniversityYemen Department of Computer Sciences&Information Ibb UniversityYemen

The attention-based encoder-decoder technique,known as the trans-former,is used to enhance the performance of end-to-end automatic speech recognition(ASR).This research focuses on applying ASR end-toend transformer-based models for the Arabic language,as the researchers’community pays little attention to *** Muslims Holy Qur’an book is written using Arabic diacritized *** this paper,an end-to-end transformer model to building a robust Qur’an *** is *** acoustic model was built using the transformer-based model as deep learning by the PyTorch framework.A multi-head attention mechanism is utilized to represent the encoder and decoder in the acoustic *** filter bank is used for feature *** build a language model(LM),the Recurrent Neural Network(RNN)and Long short-term memory(LSTM)were used to train an n-gram word-based *** a part of this research,a new dataset of Qur’an verses and their associated transcripts were collected and processed for training and evaluating the proposed model,consisting of 10 h *** recitations performed by 60 *** experimental results showed that the proposed end-to-end transformer-based model achieved a significant low character error rate(CER)of 1.98%and a word error rate(WER)of 6.16%.We have achieved state-of-the-art end-to-end transformer-based recognition for Qur’an reciters.

关键词： attention-based encoder-decoder recurrent neural network long short-term memory qur’an reciters recognition diacritized arabic text

来源：评论

学校读者我要写书评

暂无评论

Dynamic Network Slice Scaling Assisted by attention-based Prediction in 5G Core Network

引用

IEEE ACCESS 2022年 10卷 72955-72972页

作者： Chien-Nguyen Nhu Park, Minho Soongsil Univ Dept Informat Commun Convergence Technol Seoul 156743 South Korea Soongsil Univ Sch Elect Engn Seoul 156743 South Korea

Network slicing is a key technology in fifth-generation (5G) networks that allows network operators to create multiple logical networks over a shared physical infrastructure to meet the requirements of diverse use cases. Among core functions to implement network slicing, resource management and scaling are difficult challenges. Network operators must ensure the Service Level Agreement (SLA) requirements for latency, bandwidth, resources, etc for each network slice while utilizing the limited resources efficiently, i.e., optimal resource assignment and dynamic resource scaling for each network slice. Existing resource scaling approaches can be classified into reactive and proactive types. The former makes a resource scaling decision when the resource usage of virtual network functions (VNFs) exceeds a predefined threshold, and the latter forecasts the future resource usage of VNFs in network slices by utilizing classical statistical models or deep learning models. However, both have a trade-off between assurance and efficiency. For instance, the lower threshold in the reactive approach or more marginal prediction in the proactive approach can meet the requirements more certainly, but it may cause unnecessary resource wastage. To overcome the trade-off, we first propose a novel and efficient proactive resource forecasting algorithm. The proposed algorithm introduces an attention-based encoder-decoder model for multivariate time series forecasting to achieve high short-term and long-term prediction accuracies. It helps network slices be scaled up and down effectively and reduces the costs of SLA violations and resource overprovisioning. Using the attention mechanism, the model attends to every hidden state of the sequential input at every time step to select the most important time steps affecting the prediction results. We also designed an automated resource configuration mechanism responsible for monitoring resources and automatically adding or removing VNF instances

关键词： Forecasting Predictive models Time series analysis Network slicing Costs 5G mobile communication Data models Network slicing auto scaling resource prediction deep learning attention-based encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A Human-Inspired Recognition System for Pre-Modern Japanese Historical Documents

引用

IEEE ACCESS 2019年 7卷 84163-84169页

作者： Ann Duc Le Clanuwat, Tarin Kitamoto, Asanobu Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Ctr Open Data Humanities Tokyo 1018430 Japan

Recognition of historical documents is a challenging problem due to the noised, damaged characters, and background. However, in Japanese historical documents, not only contains the mentioned problems, pre-modern Japanese characters were written in cursive and are connected. Therefore, character segmentation-based methods do not work well. This leads to the idea of creating a new recognition system. In this paper, we propose a human-inspired document reading system to recognize multiple lines of pre-modern Japanese historical documents. During the reading, people employ eyes movement to determine the start of a text line. Then, they move the eyes from the current character/word to the next character/word. They can also determine the end of a line or skip a figure to move to the next line. The eyes movement integrates with visual processing to operate the reading process in the brain. We employ attention-based encoder-decoder to implement this recognition system. First, the recognition system detects were to start a text line. Second, the system scans and recognize character by character until the text line is completed. Then, the system continues to detect the start of the next text line. This process is repeated until reading the whole document. As results, the system is successful to recognize multiple lines, connected and cursive characters without performing character/line segmentation. Besides, we also employ a coverage model which stores the history of eyes movement to predict the next movement more precisely. We tested our human-inspired recognition system on the pre-modern Japanese historical document provided by the PRMU Kuzushiji competition. The results of the experiments demonstrate the superiority and effectiveness of our proposed system by achieving Sequence Error Rate of 9.87% and 53.81% on level 2 and level 3 of the dataset, respectively. These results outperform to any other systems participated in the PRMU Kuzushiji competition.

关键词： A human reading-inspired recognition system recognition of pre-modern Japanese historical document attention-based encoder-decoder Kuzushiji

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Network for Continuous Human Motion Recognition via Radar Radios

引用

IEEE SENSORS JOURNAL 2021年第5期21卷 6487-6496页

作者： Zhao, Running Ma, Xiaolin Liu, Xinhua Liu, Jian Wuhan Univ Technol Sch Informat Engn Hubei Key Lab Broadband Wireless Commun & Sensor Wuhan 430070 Peoples R China Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA

Micro-Doppler-based continuous human motion recognition (HMR) has gained considerable attention recently. However, existing methods mainly rely on individual recurrent neural network or sliding-window-based approaches, which makes them hard to effectively exploit all the temporal information to predict motions. Additionally, they need to represent the raw radar data into other domains and then perform feature extraction and classification. Thus, the representation cannot be optimized, and its high computational complexity and independence from learning model make the network consume significant time. In this article, to address these issues, we propose a new end-to-end network that uses radar radios to recognize continuous motion. Specifically, the fusion layer fuses the raw I & Q radar data without the need of representations, and it is integrated with subsequent networks in an end-to-end manner for jointly optimization. Moreover, the attention-based encoder-decoder structure encodes the fused data and selects useful temporal information for recognition, which guarantees the effective use of all the temporal information. The experiments show that in continuous HMR, the proposed network outperforms existing methods in terms of accuracy and inference time.

关键词： Radar Sensors Feature extraction Spectrogram Vibrations Convolution Data models Continuous human motion recognition micro-Doppler raw radar data deep learning end-to-end attention-based encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Alignment Knowledge Distillation for Online Streaming attention-based Speech Recognition

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2023年 31卷 1371-1385页

作者： Inaguma, Hirofumi Kawahara, Tatsuya Kyoto Univ Grad Sch Informat Kyoto 6068501 Japan

This article describes an efficient training method for online streaming attention-based encoder-decoder (AED) automatic speech recognition (ASR) systems. AED models have achieved competitive performance in offline scenarios by jointly optimizing all components. They have recently been extended to an online streaming framework via models such as monotonie chunkwise attention (MoChA). However, the elaborate attention calculation process is not robust against long-form speech utterances. Moreover, the sequence-level training objective and time-restricted streaming encoder cause a nonnegligible delay in token emission during inference. To address these problems, we propose CTC synchronous training (CTC-ST), in which CTC alignments are leveraged as a reference for token boundaries to enable a MoChA model to learn optimal monotonie input-output alignments. We formulate a purely end-to-end training objective to synchronize the boundaries of MoChA to those of CTC. The CTC model shares an encoder with the MoChA model to enhance the encoder representation. Moreover, the proposed method provides alignment information learned in the CTC branch to the attention-based decoder. Therefore, CTC-ST can be regarded as self-distillation of alignment knowledge from CTC to MoChA. Experimental evaluations on a variety of benchmark datasets show that the proposed method significantly reduces recognition errors and emission latency simultaneously. The robustness to long-form and noisy speech is also demonstrated. We compare CTC-ST with several methods that distill alignment knowledge from a hybrid ASR system and show that the CTC-ST can achieve a comparable tradeoff of accuracy and latency without relying on external alignment information.

关键词： Decoding Training Context modeling Transducers Complexity theory Speech processing Predictive models attention-based encoder-decoder connectionist temporal classification knowledge distillation monotonic chunkwise attention streaming automatic speech recognition

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：