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： Shi, Hao Mimura, Masato Wang, Longbiao Dang, Jianwu Kawahara, Tatsuya Kyoto University Graduate School of Informatics Kyoto Japan Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China

ISBN: (纸本)9781728163277

Time-domain speech enhancement (SE) has recently been intensively investigated. Among recent works, DEMUCS [1] introduces multi-resolution STFT loss to enhance performance. However, some resolutions used for STFT contain non-stationary signals, and it is challenging to learn multi-resolution frequency losses simultaneously with only one output. For better use of multi-resolution frequency information, we supplement multiple spectrograms in different frame lengths into the time-domain encoders. They extract stationary frequency information in both narrowband and wideband. We also adopt multiple decoder outputs, each of which computes its corresponding resolution frequency loss. Experimental results show that (1) it is more effective to fuse stationary frequency features than non-stationary features in the encoder, and (2) the multiple outputs consistent with the frequency loss improve performance. Experiments on the Voice-Bank dataset show that the proposed method obtained a 0.14 PESQ improvement. © 2023 IEEE.

关键词： multiresolution spectrograms Speech enhancement time domain

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Audio-Visual Co-Learning for Text-Independent Speaker Verification 48

Cross-Modal Audio-Visual Co-Learning for Text-Independent Sp...

引用

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

作者： Liu, Meng Lee, Kong Aik Wang, Longbiao Zhang, Hanyi Zeng, Chang Dang, Jianwu Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Astar Institute for Infocomm Research Singapore Singapore Institute of Technology Singapore National Institute of Informatics Tokyo Japan

ISBN: (纸本)9781728163277

Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The primary motivation of our cross-modal co-learning method is modeling one modality aided by exploiting knowledge from another modality. Specifically, two cross-modal boosters are introduced based on an audio-visual pseudo-siamese structure to learn the modality-transformed correlation. Inside each booster, a max-feature-map embedded Transformer variant is proposed for modality alignment and enhanced feature generation. The network is co-learned both from scratch and with pretrained models. Experimental results on the test scenarios demonstrate that our proposed method achieves around 60% and 20% average relative performance improvement over baseline unimodal and fusion systems, respectively. © 2023 IEEE.

关键词： co-learning cross-modal lip biometrics speaker verification visual speech

来源：评论

学校读者我要写书评

暂无评论

ONE2SET + Large Language Model: Best Partners for Keyphrase Generation

ONE2SET + Large Language Model: Best Partners for Keyphrase ...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Shao, Liangying Zhang, Liang Peng, Minlong Ma, Guoqi Yue, Hao Sun, Mingming Su, Jinsong School of Informatics Xiamen University China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Xiamen University Ministry of Culture and Tourism China Cognitive Computing Lab Baidu Research China Beijing Institute of Mathematical Sciences and Applications China

ISBN: (纸本)9798891761643

Keyphrase generation (KPG) aims to automatically generate a collection of phrases representing the core concepts of a given document. The dominant paradigms in KPG include ONE2SEQ and ONE2SET. Recently, there has been increasing interest in applying large language models (LLMs) to KPG. Our preliminary experiments reveal that it is challenging for a single model to excel in both recall and precision. Further analysis shows that: 1) the ONE2SET paradigm owns the advantage of high recall, but suffers from improper assignments of supervision signals during training;2) LLMs are powerful in keyphrase selection, but existing selection methods often make redundant selections. Given these observations, we introduce a generate-then-select framework decomposing KPG into two steps, where we adopt a ONE2SET-based model as generator to produce candidates and then use an LLM as selector to select keyphrases from these candidates. Particularly, we make two important improvements on our generator and selector: 1) we design an Optimal Transport-based assignment strategy to address the above improper assignments;2) we model the keyphrase selection as a sequence labeling task to alleviate redundant selections. Experimental results on multiple benchmark datasets show that our framework significantly surpasses state-of-the-art models, especially in absent keyphrase prediction. We release our code at https://***/DeepLearnXMU/KPG-SetLLM. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

TIME-DOMAIN SPEECH ENHANCEMENT ASSISTED BY MULTI-RESOLUTION FREQUENCY ENCODER AND DECODER

arXiv

引用

arXiv 2023年

作者： Shi, Hao Mimura, Masato Wang, Longbiao Dang, Jianwu Kawahara, Tatsuya Graduate School of Informatics Kyoto University Kyoto Japan Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Time-Domain Speech Enhancement Assisted by Multi-Resolution Frequency Encoder and Decoder

Time-Domain Speech Enhancement Assisted by Multi-Resolution ...

引用

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

作者： Hao Shi Masato Mimura Longbiao Wang Jianwu Dang Tatsuya Kawahara Graduate School of Informatics Kyoto University Kyoto Japan Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China

关键词： Time-frequency analysis Fuses Neural networks Speech enhancement Decoding Time-domain analysis Spectrogram

来源：评论

学校读者我要写书评

暂无评论

Local and Global Feature-Aware Dual-Branch Networks for Plant Disease Recognition

引用

植物表型组学（英文） 2024年第4期6卷 828-840页

作者： Jianwu Lin Xin Zhang Yongbin Qin Shengxian Yang Xingtian Wen Tomislav Cernava Quirico Migheli Xiaoyulong Chen Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China School of Biological Sciences Faculty of Environmental and Life SciencesUniversity of SouthamptonSouthampton S017 1BJUK Dipartimento di Agraria and NRD-Nucleo di Ricerca sulla Desertificazione Università degli Studi di SassariSassariItaly Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Life Sciences Guizhou UniversityGuiyang 550025China

Accurate identification of plant diseases is important for ensuring the safety of agricultural *** neural networks(CNNs)and visual transformers(VTs)can extract effective representations of images and have been widely used for the intelligent recognition of plant disease ***,CNNs have excellent local perception with poor global perception,and VTs have excellent global perception with poor local *** makes it difficult to further improve the performance of both CNNs and VTs on plant disease recognition *** this paper,we propose a local and global feature-aware dual-branch network,named LGNet,for the identification of plant *** specifically,we first design a dual-branch structure based on CNNs and VTs to extract the local and global ***,an adaptive feature fusion(AFF)module is designed to fuse the local and global features,thus driving the model to dynamically perceive the weights of different ***,we design a hierarchical mixed-scale unit-guided feature fusion(HMUFF)module to mine the key information in the features at different levels and fuse the differentiated information among them,thereby enhancing the model's multiscale perception ***,extensive experiments were conducted on the Al Challenger 2018 dataset and the self-collected corn disease(SCD)*** experimental results demonstrate that our proposed LGNet achieves state-of-the-art recognition performance on both the Al Challenger 2018 dataset and the SCD dataset,with accuracies of 88.74％and 99.08％,respectively.

关键词： global plant disease dual-branch feature-aware local networks recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Audio-Visual Co-Learning for Text-Independent Speaker Verification

Cross-Modal Audio-Visual Co-Learning for Text-Independent Sp...

引用

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

作者： Meng Liu Kong Aik Lee Longbiao Wang Hanyi Zhang Chang Zeng Jianwu Dang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Institute for Infocomm Research A⋆STAR Singapore Singapore Institute of Technology Singapore National Institute of Informatics Tokyo Japan

关键词： Visualization Correlation Biometrics (access control) Lips Production Signal processing Transformers

来源：评论

学校读者我要写书评

暂无评论

An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios

arXiv

引用

arXiv 2024年

作者： Gong, Cheng Cooper, Erica Wang, Xin Qiang, Chunyu Geng, Mengzhe Wells, Dan Wang, Longbiao Dang, Jianwu Tessier, Marc Pine, Aidan Richmond, Korin Yamagishi, Junichi Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China National Institute of Informatics Japan National Research Council Canada The Centre for Speech Technology Research University of Edinburgh United Kingdom National Institute of Information and Communications Technology Japan

Self-supervised learning (SSL) representations from massively multilingual models offer a promising solution for low-resource language speech tasks. Despite advancements, language adaptation in TTS systems remains an open problem. This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system proposed in our previous work. We conducted experiments on 12 languages using limited data with various fine-tuning configurations. We demonstrate that the similarity in phonetics between the pretraining and target languages, as well as the language category, affects the target language’s adaptation performance. Additionally, we find that the fine-tuning dataset size and number of speakers influence adaptability. Surprisingly, we also observed that using paired data for fine-tuning is not always optimal compared to audio-only data. Beyond speech intelligibility, our analysis covers speaker similarity, language identification, and predicted MOS. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

MONOLINGUAL RECOGNIZERS FUSION FOR CODE-SWITCHING SPEECH RECOGNITION

arXiv

引用

arXiv 2022年

作者： Song, Tongtong Xu, Qiang Lu, Haoyu Wang, Longbiao Shi, Hao Lin, Yuqin Yang, Yanbing Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Graduate School of Informatics Kyoto University Sakyo-ku Kyoto Japan

The bi-encoder structure has been intensively investigated in code-switching (CS) automatic speech recognition (ASR). However, most existing methods require the structures of two monolingual ASR models (MAMs) should be the same and only use the encoder of MAMs. This leads to the problem that pre-trained MAMs cannot be timely and fully used for CS ASR. In this paper, we propose a monolingual recognizers fusion method for CS ASR. It has two stages: the speech awareness (SA) stage and the language fusion (LF) stage. In the SA stage, acoustic features are mapped to two language-specific predictions by two independent MAMs. To keep the MAMs focused on their own language, we further extend the language-aware training strategy for the MAMs. In the LF stage, the BELM fuses two language-specific predictions to get the final prediction. Moreover, we propose a text simulation strategy to simplify the training process of the BELM and reduce reliance on CS data. Experiments on a Mandarin-English corpus show the efficiency of the proposed method. The mix error rate is significantly reduced on the test set after using open-source pre-trained MAMs. Copyright © 2022, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Speech Dereverberation Based on Scale-Aware Mean Square Error Loss 28th

Speech Dereverberation Based on Scale-Aware Mean Square Err...

引用

28th International Conference on Neural Information Processing, ICONIP 2021

作者： Qiang, Luya Shi, Hao Ge, Meng Yin, Haoran Li, Nan Wang, Longbiao Li, Sheng Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Graduate School of Informatics Kyoto University Sakyo-ku Kyoto Japan Kyoto Japan Japan Advanced Institute of Science and Technology Ishikawa Japan

ISBN: (纸本)9783030923068

Recently, deep learning-based speech dereverberation appro-aches have achieved remarkable performance by directly mapping the input spectrogram to a target spectrogram or time-frequency mask. However, these approaches are usually optimized under distance-related objective functions—the mean square error (MSE). The traditional MSE training criterion results in a strong inherent uniform variance statistical assumption on the target speech and noise during training, which cannot be satisfied in real-world scenarios. To alleviate such an assumption mismatch problem, we propose a speech dereverberation solution called Scale-aware Speech Dereverberation (SaSD) based on scaled-MSE. Specifically, we modify the MSE with different scales for each frequency band and progressively reduce the gap between the low- and high-frequency ranges to make the error follow the assumption of MSE assumption. Experiments demonstrated that SaSD achieved 1.0 SRMR and 0.8 PESQ improvements over the mapping baseline system. © 2021, Springer Nature Switzerland AG.

关键词： Mean square error

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：