检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

328 篇 会议
129 篇 期刊文献

馆藏范围

457 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

320 篇 工学
- 241 篇 计算机科学与技术...
- 210 篇 软件工程
- 98 篇 信息与通信工程
- 27 篇 生物工程
- 18 篇 控制科学与工程
- 17 篇 化学工程与技术
- 16 篇 电气工程
- 14 篇 电子科学与技术（可...
- 13 篇 仪器科学与技术
- 11 篇 生物医学工程（可授...
- 7 篇 机械工程
- 7 篇 建筑学
- 6 篇 安全科学与工程
- 5 篇 土木工程
- 5 篇 农业工程
170 篇 理学
- 122 篇 物理学
- 58 篇 数学
- 32 篇 生物学
- 22 篇 统计学（可授理学、...
- 17 篇 化学
- 10 篇 系统科学
78 篇 管理学
- 69 篇 图书情报与档案管...
- 6 篇 管理科学与工程(可...
15 篇 医学
- 13 篇 基础医学(可授医学...
- 13 篇 临床医学
- 8 篇 药学(可授医学、理...
- 6 篇 公共卫生与预防医...
9 篇 法学
- 7 篇 社会学
8 篇 文学
- 6 篇 中国语言文学
- 5 篇 外国语言文学
6 篇 教育学
5 篇 农学
1 篇 经济学

主题

47 篇 speech recogniti...
31 篇 speech
30 篇 training
18 篇 acoustics
14 篇 machine translat...
13 篇 decoding
12 篇 social networkin...
12 篇 speaker recognit...
11 篇 hidden markov mo...
11 篇 computational mo...
11 篇 semantics
10 篇 conferences
9 篇 speech processin...
9 篇 computational li...
9 篇 feature extracti...
9 篇 embeddings
8 篇 training data
8 篇 natural language...
8 篇 pipelines
7 篇 lattices

机构

88 篇 human language t...
54 篇 human language t...
43 篇 center for langu...
21 篇 center for langu...
20 篇 human language t...
20 篇 human language t...
18 篇 center for langu...
15 篇 human language t...
13 篇 center for langu...
12 篇 human language t...
11 篇 human language t...
10 篇 johns hopkins un...
9 篇 johns hopkins un...
8 篇 human language t...
7 篇 human language t...
7 篇 department of co...
7 篇 xiaomi corp.
6 篇 computer and inf...
6 篇 xiaomi corporati...
6 篇 center for langu...

作者

64 篇 dredze mark
50 篇 khudanpur sanjee...
43 篇 van durme benjam...
30 篇 dehak najim
27 篇 sanjeev khudanpu...
21 篇 post matt
20 篇 mcnamee paul
20 篇 hermansky hynek
20 篇 callison-burch c...
19 篇 villalba jesús
18 篇 povey daniel
16 篇 duh kevin
16 篇 mayfield james
15 篇 zelasko piotr
15 篇 daniel povey
15 篇 watanabe shinji
14 篇 wiesner matthew
14 篇 andrews nicholas
13 篇 paul michael j.
13 篇 mccree alan

语言

448 篇 英文
9 篇 其他

检索条件"机构=Human Language Technology Center of Excellence and Center for Language and Speech Processing"

共 457 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Exploring Geometric Representational Disparities Between Multilingual and Bilingual Translation Models 30

Exploring Geometric Representational Disparities Between Mul...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on language Resources and Evaluation, LREC-COLING 2024

作者： Verma, Neha Murray, Kenton Duh, Kevin Center for Language and Speech Processing United States Human Language Technology Center of Excellence United States

ISBN: (纸本)9782493814104

Multilingual machine translation has proven immensely useful for both parameter efficiency and overall performance across many language pairs via complete multilingual parameter sharing. However, some language pairs in multilingual models can see worse performance than in bilingual models, especially in the one-to-many translation setting. Motivated by their empirical differences, we examine the geometric differences in representations from bilingual models versus those from one-to-many multilingual models. Specifically, we compute the isotropy of these representations using intrinsic dimensionality and IsoScore, in order to measure how the representations utilize the dimensions in their underlying vector space. Using the same evaluation data in both models, we find that for a given language pair, its multilingual model decoder representations are consistently less isotropic and occupy fewer dimensions than comparable bilingual model decoder representations. Additionally, we show that much of the anisotropy in multilingual decoder representations can be attributed to modeling language-specific information, therefore limiting remaining representational capacity. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

JHU IWSLT 2024 Dialectal and Low-resource System Description 21

JHU IWSLT 2024 Dialectal and Low-resource System Description

引用

21st International Conference on Spoken language Translation, IWSLT 2024

作者： Robinson, Nathaniel R. Sun, Kaiser Xiao, Cihan Bafna, Niyati Tan, Weiting Xu, Haoran Xinyuan, Henry Li Kejriwal, Ankur Khudanpur, Sanjeev Murray, Kenton McNamee, Paul Johns Hopkins University Center for Language and Speech Processing United States Human Language Technology Center of Excellence Baltimore United States

ISBN: (纸本)9798891761414

Johns Hopkins University (JHU) submitted systems for all eight language pairs in the 2024 Low-Resource language Track. The main effort of this work revolves around fine-tuning large and publicly available models in three proposed systems: i) end-to-end speech translation (ST) fine-tuning of SEAMLESSM4T v2;ii) ST fine-tuning of Whisper;iii) a cascaded system involving automatic speech recognition with fine-tuned Whisper and machine translation with NLLB. On top of systems above, we conduct a comparative analysis of different training paradigms, such as intra-distillation of NLLB, joint training and curriculum learning of SEAMLESSM4T v2, and multi-task learning and pseudo-translation with Whisper. Our results show that the best-performing approach differs by language pairs, but that i) fine-tuned SEAMLESSM4T v2 tends to perform best for source languages on which it was pre-trained, ii) multitask training helps Whisper fine-tuning, iii) cascaded systems with Whisper and NLLB tend to outperform Whisper alone, and iv) intra-distillation helps NLLB fine-tuning. ©2024 Association for Computational Linguistics.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Adapting Self-Supervised Models to Multi-Talker speech Recognition Using Speaker Embeddings 48

Adapting Self-Supervised Models to Multi-Talker Speech Recog...

引用

48th IEEE International Conference on Acoustics, speech and Signal processing, ICASSP 2023

作者： Huang, Zili Raj, Desh Garcia, Paola Khudanpur, Sanjeev Johns Hopkins University Center for Language and Speech Processing Human Language Technology Center of Excellence Baltimore United States

ISBN: (纸本)9781728163277

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-Talker applications. However, these models often have degraded performance for multi-Talker scenarios-possibly due to the domain mismatch-which severely limits their use for such applications. In this paper, we investigate the adaptation of upstream SSL models to the multi-Talker automatic speech recognition (ASR) task under two conditions. First, when segmented utterances are given, we show that adding a target speaker extraction (TSE) module based on enrollment embeddings is complementary to mixture-Aware pre-Training. Second, for unsegmented mixtures, we propose a novel joint speaker modeling (JSM) approach, which aggregates information from all speakers in the mixture through their embeddings. With controlled experiments on Libri2Mix, we show that using speaker embeddings provides relative WER improvements of 9.1% and 42.1% over strong baselines for the segmented and unsegmented cases, respectively. We also demonstrate the effectiveness of our models for real conversational mixtures through experiments on the AMI dataset. Our code and models are open-sourced on https://***/HuangZiliAndy/SSL_for_multitalker. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

JHU IWSLT 2023 Dialect speech Translation System Description 20

JHU IWSLT 2023 Dialect Speech Translation System Description

引用

20th International Conference on Spoken language Translation, IWSLT 2023

作者： Hussein, Amir Xiao, Cihan Verma, Neha Thebaud, Thomas Wiesner, Matthew Khudanpur, Sanjeev Center for Language and Speech Processing United States Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781959429845

This paper presents JHU’s submissions to the IWSLT 2023 dialectal and low-resource track of Tunisian Arabic to English speech translation. The Tunisian dialect lacks formal orthography and abundant training data, making it challenging to develop effective speech translation (ST) systems. To address these challenges, we explore the integration of large pretrained machine translation (MT) models, such as mBART and NLLB-200 in both end-to-end (E2E) and cascaded speech translation (ST) systems. We also improve the performance of automatic speech recognition (ASR) through the use of pseudo-labeling data augmentation and channel matching on telephone data. Finally, we combine our E2E and cascaded ST systems with Minimum Bayes-Risk decoding. Our combined system achieves a BLEU score of 21.6 and 19.1 on test2 and test3, respectively. © IWSLT *** rights reserved.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

JHU IWSLT 2023 Multilingual speech Translation System Description 20

JHU IWSLT 2023 Multilingual Speech Translation System Descri...

引用

20th International Conference on Spoken language Translation, IWSLT 2023

作者： Xinyuan, Henry Li Verma, Neha Odoom, Bismarck Bamfo Pradeep, Ujvala Wiesner, Matthew Khudanpur, Sanjeev Center for Language and Speech Processing United States Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781959429845

We describe the Johns Hopkins ACL 60-60 speech Translation systems submitted to the IWSLT 2023 Multilingual track, where we were tasked to translate ACL presentations from English into 10 languages. We developed cascaded speech translation systems for both the constrained and unconstrained subtracks. Our systems make use of pre-trained models as well as domain-specific corpora for this highly technical evaluation-only task. We find that the specific technical domain which ACL presentations fall into presents a unique challenge for both ASR and MT, and we present an error analysis and an ACL-specific corpus we produced to enable further work in this area. © IWSLT *** rights reserved.

关键词： Petroleum reservoir evaluation

来源：评论

学校读者我要写书评

暂无评论

Importance of Different Temporal Modulations of speech: a Tale of two Perspectives 48

Importance of Different Temporal Modulations of Speech: a Ta...

引用

48th IEEE International Conference on Acoustics, speech and Signal processing, ICASSP 2023

作者： Sadhu, Samik Hermansky, Hynek Johns Hopkins University Center for Language and Speech Processing United States Johns Hopkins University Human Language Technology Center of Excellence United States

ISBN: (纸本)9781728163277

How important are different temporal speech modulations for speech recognition? We answer this question from two complementary perspectives. Firstly, we quantify the amount of phonetic information in the modulation spectrum of speech by computing the mutual information between temporal modulations with frame-wise phoneme labels. Looking from another perspective, we ask - which speech modulations an Automatic speech Recognition (ASR) system prefers for its operation. Data-driven weights are learned over the modulation spectrum and optimized for an end-to-end ASR task. Both methods unanimously agree that speech information is mostly contained in slow modulation. Maximum mutual information occurs around 3-6 Hz which also happens to be the range of modulations most preferred by the ASR. In addition, we show that the incorporation of this knowledge into ASRs significantly reduces their dependency on the amount of training data. © 2023 IEEE.

关键词： Modulation Training data speech recognition Phonetics Acoustics Task analysis speech processing

来源：评论

学校读者我要写书评

暂无评论

Identifying Context-Dependent Translations for Evaluation Set Production 8

Identifying Context-Dependent Translations for Evaluation Se...

引用

8th Conference on Machine Translation, WMT 2023

作者： Wicks, Rachel Post, Matt Human Language Technology Center of Excellence Johns Hopkins University United States Center of Language and Speech Processing Johns Hopkins University United States Microsoft United States

ISBN: (纸本)9798891760417

A major impediment to the transition to context-aware machine translation is the absence of good evaluation metrics and test sets. Sentences that require context to be translated correctly are rare in test sets, reducing the utility of standard corpus-level metrics such as COMET or BLEU. On the other hand, datasets that annotate such sentences are also rare, small in scale, and available for only a few languages. To address this, we modernize, generalize, and extend previous annotation pipelines to produce CTXPRO, a tool that identifies subsets of parallel documents containing sentences that require context to correctly translate five phenomena: gender, formality, and animacy for pronouns, verb phrase ellipsis, and ambiguous noun inflections. The input to the pipeline is a set of handcrafted, per-language, linguistically-informed rules that select contextual sentence pairs using coreference, part-of-speech, and morphological features provided by state-of-the-art tools. We apply this pipeline to seven languages pairs (EN into and out-of DE, ES, FR, IT, PL, PT, and RU) and two datasets (OpenSubtitles and WMT test sets), and validate its performance using both overlap with previous work and its ability to discriminate a contextual MT system from a sentence-based one. We release the CTXPRO pipeline and data as open source. © 2023 Association for Computational Linguistics.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Building Keyword Search System from End-To-End Asr Systems 48

Building Keyword Search System from End-To-End Asr Systems

引用

48th IEEE International Conference on Acoustics, speech and Signal processing, ICASSP 2023

作者： Huang, Ruizhe Wiesner, Matthew Garcia-Perera, Leibny Paola Povey, Dan Trmal, Jan Khudanpur, Sanjeev Johns Hopkins University Center for Language and Speech Processing United States Johns Hopkins University Human Language Technology Center of Excellence United States Xiaomi Corporation Beijing China

ISBN: (纸本)9781728163277

Keyword search (KWS) systems are commonly built on top of existing automatic speech recognition (ASR) systems. However, end-to-end (E2E) ASR models are not naturally equipped with word-level timing information or confidence. Existing methods for re-purposing E2E ASR systems for KWS are largely heuristic or model-specific. In this paper, we describe a general KWS pipeline, applicable to any ASR model that generates N-best lists. We extract timing information using either external word-aligners, or time-preserving weighted finite-state transducer-based decoders. We show that our light-weight, ASR-agnostic approach for confidence estimation based on N-best lists outperforms other commonly used heuristics, such as using the decoder's softmax probability, and even a more complicated dedicated confidence estimation model (CEM). Finally, we compare our performance to hybrid ASR models, extensively evaluating the impact of word-level timing, confidence, and recall on KWS performance. Our KWS pipeline is available online1, suitable for evaluating the aforementioned ASR components as downstream tasks. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Does Sentence Segmentation Matter for Machine Translation? 7

Does Sentence Segmentation Matter for Machine Translation?

引用

7th Conference on Machine Translation, WMT 2022

作者： Wicks, Rachel Post, Matt Center for Language and Speech Processing United States Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781959429296

For the most part, NLP applications operate at the sentence level. Since sentences occur most naturally not on their own but embedded in documents, they must be extracted and segmented via the use of a segmenter, of which there are a handful of options. There has been some work evaluating the performance of segmenters on intrinsic metrics, that look at their ability to recover human-segmented sentence boundaries, but there has been no work looking at the effect of segmenters on downstream tasks. We ask the question, "does segmentation matter?" and attempt to answer it on the task of machine translation. We consider two settings: the inference scenario, where sentences are passed into a black-box system whose training segmentation is mostly unknown, and the training setting, where researchers have full control over the process. We find that the choice of segmenter largely does not matter, so long as its behavior is not one of extreme under- or over-segmentation. For such settings, we provide some qualitative analysis examining their harms, and point the way towards document-level processing. © 2022 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HLTCOE Submission to the VoicePrivacy Attacker Challenge

HLTCOE Submission to the VoicePrivacy Attacker Challenge

引用

2025 IEEE International Conference on Acoustics, speech, and Signal processing, ICASSP 2025

作者： Xinyuan, Henry Li Garg, Ashi Cai, Zexin Duh, Kevin García-Perera, Leibny Paola Khudanpur, Sanjeev Andrews, Nicholas Wiesner, Matthew Human Language Technology Center of Excellence Johns Hopkins University Baltimore United States

ISBN: (纸本)9798350368741

We describe our submission to the 2024 VoicePrivacy Attacker Challenge. We propose three main categories of methods to improve ASV performance against anonymized speech: improvements to the underlying classifier, alternative distance metrics when computing ASV scores, and kNN-VC normalization. By simultaneously employing one or more of these methods, we were able to achieve a significant reduction in EER against all of the submitted anonymization systems in the VoicePrivacy Challenge. © 2025 IEEE.

关键词： Automatic Speaker Verification speech Anonymization

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共46页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：