检索结果-内蒙古大学图书馆

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Improving the vocabulary learning by personalized proficiency 12

Improving the vocabulary learning by personalized proficienc...

引用

12th International Conference on Ubi-Media computing, Ubi-Media 2019

作者： Lin, Yi-Zhen Chen, Kai-Hsiang Huang, Jen-Wei Department of Electrical Engineering National Cheng Kung University Tainan Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan

ISBN: (纸本)9781728128207

To improve the vocabulary ability is very important in language learning. Thus, if we can learn and remember a word very effectively, then we will be able to master a language more quickly. Therefore, many scholars began to propose related research. Due to the learning mechanism of human brain, sometimes when people learn a new knowledge they may forgot at a short time. In order to make the consideration more complete, after analyzing Hermann Ebbinghaus's forgetting curve experiment, we added two variables, one is the acceptance of each word by the same person, and the other is the ability of different people to remember vocabulary. With the above two parameters, we want to design a system to help user to review the vocabulary which may be forgetting before. The forgetting curve can be personalized, and it is more accurate to calculate the best time for each user to review the vocabulary. © 2019 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Improvement of Spatial Ambiguity in Multi-Channel Speech Separation Using Channel Attention

Improvement of Spatial Ambiguity in Multi-Channel Speech Sep...

引用

2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021

作者： Hong, Qian-Bei Wu, Chung-Hsien Nguyen, Thanh Binh Wang, Hsin-Min National Cheng Kung University and Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9789881476890

Multi-channel speech separation has been successfully applied in a complex real-world environment such as the far-field condition. The common solution to deal with the far-field condition is using a multi-channel signal captured by a structured microphone array and leveraging the inner difference between channels to enhance the speech separation performance. The spatial feature has been widely used in recent speech separation research. This feature appears to be insufficient when the location information becomes ambiguous. This is known as the spatial ambiguity problem. In order to deal with the spatial ambiguity problem, this study proposes an attention mechanism for the Temporal-Spatial Neural Filter (TSNF), in which the channel attention on merged features and the feature map of 1D convolution block in the temporal convolution network is proposed. The proposed method is evaluated on the multi-channel reverberant dataset which is built based on the WSJ0-2mix dataset. The dataset is simulated in the real-environment room by using the Room Impulse Response generator. In the experimental results, the proposed methods produced the SI -SNR improvement of about 1.2dB in close speakers' case, while a small decrease of 0.1dB in other cases. © 2021 APSIPA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

HAEE: Question Classification Using Hierarchical Intra-Attention Enhancement Encoder

HAEE: Question Classification Using Hierarchical Intra-Atten...

引用

26th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2021

作者： Wang, Jen-Wei Chen, Kai-Hsiang Huang, Jen-Wei National Cheng Kung University Department of Electrical Engineering Tainan Taiwan National Cheng Kung University and Academia Sinica Graduate Program for Multimedia Systems and Intelligent Computing Taiwan

ISBN: (纸本)9781665408257

With the development of E-commerce, an Automated Question-Answering system takes a crucial part in customer service. Question classification, which assigns labels to questions according to the answer types, is one of the tasks in question answering. Previous methods usually used handcraft features like named entity recognition, but it needs the predefined dictionary or tools. The machine learning approaches are recently applied to this task and achieve high accuracy. In this paper, we proposed HAEE, a Hierarchical intra-Attention Enhancement Encoder which composed of bidirectional GRUs and intra-attentions. In addition, we adopt the character input to address the issue of the OOV (Out-Of-Vocabulary) problem and create multiple intra-attentions to simulate the certain relationships between characters (Chinese) or words (English) to enhance the influence of tokens on the sentence. We evaluate the HAEE model in an actual corporate setting and several datasets. As shown in the experimental results, our HAEE model outperforms the existing state-of-the-art models on question classification tasks, especially for the Chinese corpus. © 2021 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Acoustic and Textual Data Augmentation for Code-Switching Speech Recognition in Under-Resourced Language

Acoustic and Textual Data Augmentation for Code-Switching Sp...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： I-Ting Hsieh Chung-Hsien Wu Chun-Huang Wang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Tainan Taiwan

ISBN: (数字)9789881476883

ISBN: (纸本)9781728181301

Under-resourced and code-switching speech recognition have recently received research interest, resulting in several robust acoustic and language modeling approaches. As Taiwanese and Mandarin have been popularly and widely used in Taiwan, this paper aims to address the under-resourced and codeswitching issues. First, phone sharing between Taiwanese and Mandarin is employed for acoustic data augmentation to construct the acoustic models of Taiwanese speech recognizer. Regarding the lack of Taiwanese text corpus, this paper translates Mandarin corpus into Taiwanese corpus based on word-to-word translation. Moreover, additional translation rules for codeswitching text are manually designed. The augmented text corpus is then used for training the code-switching language models. In the experimental results, the word error rate for code-switching speech recognition was 26.02%, which was better than that trained by the pure Taiwanese corpus.

关键词： Speech recognition Training Acoustics Switches Mathematical model Speech coding Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 1745-1757页

作者： Hong, Qian-Bei Wu, Chung-Hsien Wang, Hsin-Min National Cheng Kung University and Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701 Taiwan Academia Sinica Taipei115 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Academia Sinica Institute of Information Science Taipei115 Taiwan

Speech content is closely related to the stability of speaker embeddings in speaker verification tasks. In this paper, we propose a novel architecture based on self-constraint learning (SCL) and reconstruction task (RT) to remove the influence of phonetic information on speaker embedding generation. First, SCL is used to reduce the divergence of frame-level features, which can avoid ambiguity between the resulting embeddings of the two utterances being compared. Second, RT is used to further remove phonetic information in frame-level layers, focusing on speaker-discriminative feature transformation. In our experiments, the speaker embedding models were trained on the VoxCeleb2 dataset and evaluated on the VoxCeleb1, Librispeech, SITW and VoxMovies datasets. Experimental results on VoxCeleb1 show that the proposed DROP-TDNN system reduced the EER by 7.5%, compared to the state-of-the-art ECAPA-TDNN system. Furthermore, the proposed DROP-TDNN system also outperformed the ECAPA-TDNN system in the experiments on SITW, Librispeech and VoxMovies under cross-dataset conditions. In the experiments on SITW, the proposed system reduced the EER by 3.4% compared to the ECAPA-TDNN system. In the experiments on Librispeech, the proposed system demonstrated the advantage of removing phonetic information under the clean speech condition, with a significant reduction of 25.5% in EER compared to the ECAPA-TDNN system. In the experiments on VoxMovies, the proposed system reduced the EER by up to 7.9% compared to the ECAPA-TDNN system under different pronunciation and background conditions. © 2014 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

HAEE: Question Classification Using Hierarchical Intra-Attention Enhancement Encoder

HAEE: Question Classification Using Hierarchical Intra-Atten...

引用

International Conference on Technologies and Applications of Artificial Intelligence (TAAI)

作者： Jen-Wei Wang Kai-Hsiang Chen Jen-Wei Huang National Cheng Kung University Tainan Taiwan Graduate Program for Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

ISBN: (纸本)9781665408264

关键词： Dictionaries Customer services Machine learning Predictive models Electronic commerce Task analysis

来源：评论

学校读者我要写书评

暂无评论

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 2824-2835页

作者： Chiu, Ching-Yu Muller, Meinard Davies, Matthew E. P. Su, Alvin Wen-Yu Yang, Yi-Hsuan National Cheng Kung University Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701401 Taiwan International Audio Laboratories Erlangen Erlangen91058 Germany University of Coimbra Department of Informatics Engineering Centre for Informatics and Systems Coimbra3004-531 Portugal National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Taiwan AI Labs Yating Music Team Taipei103622 Taiwan Academia Sinica Research Center for IT Innovation Taipei11529 Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use 'post-processing trackers' (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called 'predominant local pulses' (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2014 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Improvement of Spatial Ambiguity in Multi-Channel Speech Separation Using Channel Attention

Improvement of Spatial Ambiguity in Multi-Channel Speech Sep...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Qian-Bei Hong Chung-Hsien Wu Thanh Binh Nguyen Hsin-Min Wang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781665441629

关键词： Convolution Information processing Speech enhancement Information filters Microphone arrays Generators Reliability

来源：评论

学校读者我要写书评

暂无评论

Combining Deep Embeddings of Acoustic and Articulatory Features for Speaker Identification

Combining Deep Embeddings of Acoustic and Articulatory Featu...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Qian-Bei Hong Chung-Hsien Wu Hsin-Min Wang Chien-Lin Huang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan PingAn AI Lab Palo Alto CA USA

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

In this study, deep embedding of acoustic and articulatory features are combined for speaker identification. First, a convolutional neural network (CNN)-based universal background model (UBM) is constructed to generate acoustic feature (AC) embedding. In addition, as the articulatory features (AFs) represent some important phonological properties during speech production, a multilayer perceptron (MLP)-based AF embedding extraction model is also constructed for AF embedding extraction. The extracted AC and AF embeddings are concatenated as a combined feature vector for speaker identification using a fully-connected neural network. This proposed system was evaluated by three corpora consisting of King-ASR, LibriSpeech and SITW, and the experiments were conducted according to the properties of the datasets. We adopted all three corpora to evaluate the effect of AF embedding, and the results showed that combining AF embedding into the input feature vector improved the performance of speaker identification. The LibriSpeech corpus was used to evaluate the effect of the number of enrolled speakers. The proposed system achieved an EER of 7.80% outperforming the method based on x-vector with PLDA (8.25%). And we further evaluated the effect of signal mismatch using the SITW corpus. The proposed system achieved an EER of 25.19%, which outperformed the other baseline methods.

关键词：

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：