检索结果-内蒙古大学图书馆

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Yongmao Zhang Guanghou Liu Yi Lei Yunlin Chen Hao Yin Lei Xie Zhifei Li Audio Speech and Language Processing Group (ASLP@NPU) School of Computer Science Northwestern Polytechnical University Xi’an China Shanghai Mobvoi Information Technology Co. Ltd

Recently, text-guided content generation has received extensive attention. In this work, we explore the possibility of text description-based speaker generation, i.e., using text prompts to control the speaker generation process. Specifically, we propose PromptSpeaker, a text-guided speaker generation system. PromptSpeaker consists of a prompt encoder, a zero-shot VITS, and a Glow model, where the prompt encoder predicts a prior distribution based on the text description and samples from this distribution to obtain a semantic representation. The Glow model subsequently converts the semantic representation into a speaker representation, and the zero-shot VITS finally synthesizes the speaker’s voice based on the speaker representation. We verify that PromptSpeaker can generate speakers new from the training set by objective metrics, and the synthetic speaker voice has reasonable subjective matching quality with the speaker prompt. Our audio samples are available on the demo website 1 . 1 Demo: https://***/demo/

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spontts: Modeling and Transferring Spontaneous Style for TTS

Spontts: Modeling and Transferring Spontaneous Style for TTS

引用

International Conference on Acoustics, speech, and Signal processing (ICASSP)

作者： Hanzhao Li Xinfa Zhu Liumeng Xue Yang Song Yunlin Chen Lei Xie School of Computer Science Audio Speech and Language Processing Group (ASLP@NPU) Northwestern Polytechnical University Xi’an China School of Data Science The Chinese University of Hong Kong China Shanghai Mobvoi Information Technology Co. Ltd

Spontaneous speaking style exhibits notable differences from other speaking styles due to various spontaneous phenomena (e.g., filled pauses, prolongation) and substantial prosody variation (e.g., diverse pitch and duration variation, occasional non-verbal speech like a smile), posing challenges to modeling and prediction of spontaneous style. Moreover, the limitation of high-quality spontaneous data constrains spontaneous speech generation for speakers without spontaneous data. To address these problems, we propose SponTTS, a two-stage approach based on neural bottleneck (BN) features to model and transfer spontaneous style for TTS. In the first stage, we adopt a Conditional Variational Autoencoder (CVAE) to capture spontaneous prosody from a BN feature and involve the spontaneous phenomena by the constraint of spontaneous phenomena embedding prediction loss. Besides, we introduce a flow-based predictor to predict a latent spontaneous style representation from the text, which enriches the prosody and context-specific spontaneous phenomena during inference. In the second stage, we adopt a VITS-like module to transfer the spontaneous style learned in the first stage to the target speakers. Experiments demonstrate that SponTTS is effective in modeling spontaneous style and transferring the style to the target speakers, generating spontaneous speech with high naturalness, expressiveness, and speaker similarity. The zero-shot spontaneous style TTS test further verifies the generalization and robustness of SponTTS in generating spontaneous speech for unseen speakers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Concurrent validity of instrumented insoles measuring gait and balance metrics in Parkinson's disease 46

Concurrent validity of instrumented insoles measuring gait a...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Watkinson, Sophia A. Anderson, Anthony Caiola, Michael Eguren, David Gonzalez, Michael Velazquez, Laureano Moro Dehak, Najim Motley, Chelsea Moukheiber, Emile Mills, Kelly Muir, Brittney Butala, Ankur Kontson, Kimberly Us Food and Drug Administration Division of Biomedical Physics Silver SpringMD United States Johns Hopkins University Center for Language and Speech Processing BaltimoreMD United States Johns Hopkins University Department of Electrical and Computer Engineering BaltimoreMD United States Johns Hopkins University School of Medicine Department of Neurology BaltimoreMD United States Center for Limb Loss and Mobility Department of Veterans Affairsy SeattleWA United States

ISBN: (纸本)9798350371499

Several commercially available instrumented insole systems have been examined for validity and repeatability, but very few studies have focused on validation of the Moticon OpenGo sensor insoles in measuring gait and balance parameters in a clinical population. Given the paucity of studies examining the validity of these novel technologies in PD, there were two main goals of this research: (1) assess the concurrent validity of the Moticon OpenGo sensor insoles for gait and balance assessment in people with PD using a pressure-sensitive electronic walkway (Protokinetics Zeno™ walkway) as a reference system and (2) compare the gait metrics derived from the insole and walkway systems during a walking and turning task in order to assess the output of the systems under more real-world conditions. Twelve participants (5F/7M;mean age 71.3 ± 6.8 years) with a diagnosis of Parkinson's disease and a score of 2.5 or 3 on the Modified Hoehn & Yahr score performing straight-line walking, walking with turning, and balance tasks were included in this analysis. Differences in the estimated gait metrics from each system were evaluated through Bland-Altman analysis and calculation of Pearson's correlation coefficient (r). Results showed strong agreement between the insoles and the reference walkway system during both self-selected pace and hurried pace walking tasks. Although agreement is not as strong when estimating spatial metrics, the limits of agreement (LOA) still indicate that clinically important differences can be seen. Additional investigation into the insole derived center of pressure metrics from the insole sensor systems may be necessary as well as investigation into improved algorithms for capturing gait metrics during more real-world conditions in both types of systems. © 2024 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

PQLM - Multilingual Decentralized Portable Quantum language Model

PQLM - Multilingual Decentralized Portable Quantum Language ...

引用

International Conference on Acoustics, speech, and Signal processing (ICASSP)

作者： Shuyue Stella Li Xiangyu Zhang Shu Zhou Hongchao Shu Ruixing Liang Hexin Liu Leibny Paola Garcia Center for Language and Speech Processing Johns Hopkins University Department of Physics Hong Kong University of Science and Technology School of Electrical and Electronic Engineering Nanyang Technological University Human Language Technology Center of Excellence Johns Hopkins University

With careful manipulation, malicious agents can reverse engineer private information encoded in pre-trained language models. Security concerns motivate the development of quantum pre-training. In this work, we propose a highly portable quantum language model (PQLM) that can easily transmit information to downstream tasks on classical machines. The framework consists of a cloud PQLM built with random Variational Quantum Classifiers (VQC) and local models for downstream applications. We demonstrate the ad hoc portability of the quantum model by extracting only the word embeddings and effectively applying them to downstream tasks on classical machines. Our PQLM exhibits comparable performance to its classical counterpart on both intrinsic evaluation (loss, perplexity) and extrinsic evaluation (multilingual sentiment analysis accuracy) metrics. We also perform ablation studies on the factors affecting PQLM performance to analyze model stability. Our work establishes a theoretical foundation for a portable quantum pre-trained language model that could be trained on private data and made available for public use with privacy protection guarantees.

关键词： Training Sentiment analysis Social networking (online) Computational modeling Signal processing Stability analysis Servers

来源：评论

学校读者我要写书评

暂无评论

END-TO-END LYRICS RECOGNITION WITH SELF-SUPERVISED LEARNING

arXiv

引用

arXiv 2022年

作者： Zhang, Xiangyu Li, Shuyue Stella He, Zhanhong Togneri, Roberto Garcia, Leibny Paola Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States Department of Computer Science University of Western Australia Australia

Lyrics recognition is an important task in music processing. Despite traditional algorithms such as the hybrid HMM-TDNN model achieving good performance, studies on applying end-to-end models and self-supervised learning (SSL) are limited. In this paper, we first establish an end-to-end baseline for lyrics recognition and then explore the performance of SSL models on lyrics recognition task. We evaluate a variety of upstream SSL models with different training methods (masked reconstruction, masked prediction, autoregressive reconstruction, and contrastive learning). Our end-to-end self-supervised models, evaluated on the DAMP music dataset, outperform the previous state-of-the-art (SOTA) system by 5.23% for the dev set and 2.4% for the test set even without a language model trained by a large corpus. Moreover, we investigate the effect of background music on the performance of self-supervised learning models and conclude that the SSL models cannot extract features efficiently in the presence of background music. Finally, we study the out-of-domain generalization ability of the SSL features considering that those models were not trained on music datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Capturing short-range and long-range dependencies of nucleotides for identifying RNA N6-methyladenosine modification sites

引用

computers in Biology and Medicine 2025年 186卷 109625-109625页

作者： Li, Guodong Zhao, Bowei Su, Xiaorui Yang, Yue Zeng, Zhi Hu, Pengwei Hu, Lun Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Science Urumqi 830011 China University of Chinese Academy of Sciences Beijing 100049 China Xinjiang Laboratory of Minority Speech and Language Information Processing Urumqi 830011 China College of Computer Science and Technology Xi'an Jiaotong University Xi'an 710049 China

N6-methyladenosine (m6A) plays a crucial role in enriching RNA functional and genetic information, and the identification of m6A modification sites is therefore an important task to promote the understanding of RNA epigenetics. In the identification process, current studies are mainly concentrated on capturing the short-range dependencies between adjacent nucleotides in RNA sequences, while ignoring the impact of long-range dependencies between non-adjacent nucleotides for learning high-quality representation of RNA sequences. In this work, we propose an end-to-end prediction model, called m6ASLD, to improve the identification accuracy of m6A modification sites by capturing the short-range and long-range dependencies of nucleotides. Specifically, m6ASLD first encodes the type and position information of nucleotides to construct the initial embeddings of RNA sequences. A self-correlation map is then generated to characterize both short-range and long-range dependencies with a designed map generating block for each RNA sequence. After that, m6ASLD learns the global and local representations of RNA sequences by using a graph convolution process and a designed dependency searching block respectively, and finally achieves its identification task under a joint training scheme. Extensive experiments have demonstrated the promising performance of m6ASLD on 11 benchmark datasets across several evaluation metrics. © 2025 Elsevier Ltd

关键词： RNA sequences m 6A modification sites Nucleotide dependencies End-to-end prediction Representation learning

来源：评论

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for speech Source Separation

EDSep: An Effective Diffusion-Based Method for Speech Source...

引用

International Conference on Acoustics, speech, and Signal processing (ICASSP)

作者： Jinwei Dong Xinsheng Wang Qirong Mao School of Computer Science and Communication Engineering Jiangsu University Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi’an China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Zhenjiang China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method’s superior performance over existing diffusion and discriminative models, validating its efficacy.

关键词： Training Adaptation models Technological innovation Source separation Databases Stochastic processes Differential equations speech enhancement Diffusion models Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Approximating to the Real Translation Quality for Neural Machine Translation via Causal Motivated Methods

引用

ACM Transactions on Asian and Low-Resource language Information processing 2023年第5期22卷 1-26页

作者： Xuewen Shi Heyan Huang Ping Jian Yi-Kun Tang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Haidian District Beijing China

It is hard to evaluate translations objectively and accurately, which limits the applications of machine translation. In this article, we assume that the above phenomenon is caused by noise interference during translation evaluation, and we handle the problem through a perspective of causal inference. We assume that the observable translation score is affected by the unobservable true translation quality and some noise simultaneously. If there is a variable that is related to the noise and independent to the true translation quality, the related noise can be eliminated by removing the effect of that variable from the observed score. Based on the above causality hypothesis, this article studies the length bias problem of beam search for neural machine translation (NMT) and the input related noise problem of translation quality estimation (QE). For the NMT length bias problem, we conduct the experiments on four typical NMT tasks (Uyghur–Chinese, Chinese–English, English–German, and English–French) with different scales of datasets. Comparing with previous approaches, the proposed causal motivated method is model-agnostic and does not require supervised training. For QE tasks, we conduct the experiments on the WMT’20 submissions. Experimental results show that the denoised QE results gain better Pearson’s correlation scores with human assessed scores compared to the original submissions. Further analyses on the NMT and QE tasks also demonstrate the rationality of the empirical assumptions made on our methods.

关键词： Neural machine translation causal inference half-sibling regression quality estimation

来源：评论

学校读者我要写书评

暂无评论

Isarn Dialect Word Segmentation using Bi-directional Gated Recurrent Unit with transfer learning approach

Isarn Dialect Word Segmentation using Bi-directional Gated R...

引用

International computer science and Engineering Conference (ICSEC)

作者： Sawetsit Aim-Nang Pusadee Seresangtakul Pongsathon Janyoi Department of Computer Science Natural Language and Speech Processing Laboratory College of Computing Khon Kaen University Khon Kaen Thailand

ISBN: (纸本)9781665462730

This paper presents an Isarn dialect word segmentation based on a recurrent neural network. In this study, the Isarn text written in Thai script is taken as input. We explored the effectiveness of the types of recurrent layers; recurrent neural networks (RNN), gated recurrent units (GRU), and long short-term memory (LSTM). The F1-scores of RNN, GRU, and LSTM are 95.36, 96.05, and 95.70, respectively. The experiment results showed that using GRU as the recurrent layer achieved the best performance. To deal with borrowed words from Thai, transfer learning was applied to improve the performance of the model by fine-tuning the pre-trained model given the limited size of the Isarn corpus. The model trained through the transfer learning approach outperformed the model trained from the Isarn dataset alone.

关键词： Training computer science Recurrent neural networks Protocols Computational modeling Transfer learning Bidirectional control

来源：评论

学校读者我要写书评

暂无评论

Speaker Contrastive Learning For Source Speaker Tracing

Speaker Contrastive Learning For Source Speaker Tracing

引用

IEEE Spoken language Technology Workshop

作者： Qing Wang Hongmei Guo Jian Kang Mengjie Du Jie Li Xiao-Lei Zhang Lei Xie Audio Speech and Language Processing Group (ASLP@NPU) School of Computer Science Northwestern Polytechnical University Xi’an China China Telecom Institute of Artificial Intelligence (TeleAI) China School of Marine Science and Technology Northwestern Polytechnical University Xi’an China

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

As a form of biometric authentication technology, the security of speaker verification (SV) systems is of utmost importance. However, SV systems are inherently vulnerable to various types of attacks that can compromise their accuracy and reliability. One such attack is voice conversion (VC), which modifies a person’s speech to sound like another person by altering various vocal characteristics. This poses a significant threat to SV systems. To address this challenge, the Source Speaker Tracing Challenge (SSTC) in IEEE SLT2024 aims to identify the source speaker information in manipulated speech signals. Specifically, SSTC focuses on source speaker verification against voice conversion to determine whether two converted speech samples originate from the same source speaker. In this study, we propose a speaker contrastive learning-based approach for source speaker tracing to learn the latent source speaker information in converted speech. To learn a more source-speaker-related representation, we employ speaker contrastive loss during the training of the embedding extractor. This speaker contrastive loss helps identify the true source speaker embedding among several distractor speaker embeddings, enabling the embedding extractor to learn the potentially possessing source speaker information present in the converted speech. Experiments demonstrate that our proposed speaker contrastive learning system achieves the lowest EER of 16.788% on the challenge test set, securing first place in the challenge.

关键词： Training Accuracy Conferences Contrastive learning Biometric authentication Data mining Security Reliability

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：