Improving basic methods of automatic speech recognition
改进自动语音识别的基本方法
基本信息
- 批准号:914-2008
- 负责人:
- 金额:$ 3.83万
- 依托单位:
- 依托单位国家:加拿大
- 项目类别:Discovery Grants Program - Individual
- 财政年份:2012
- 资助国家:加拿大
- 起止时间:2012-01-01 至 2013-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The biggest problem in automatic speech recognition (ASR) is robustness - making sure that ASR models are general enough. A robust ASR system should be able to decode speech from any speaker, in any reasonable environment. In practice, speakers other than those that trained the ASR models lead to a significant decrease in ASR accuracy. As well, environmental noise (e.g., weather, other talkers, cars) and communication distortions (e.g., with mobile phones) degrade ASR performance, often severely. Even simple microphone substitution reduces accuracy. Human listeners, in contrast, often can adapt rapidly to all these difficulties, which strongly suggests that major flaws exist in current ASR schemes. While it is not necessary to directly mimic human perception when designing ASR systems, much of what we know about human speech production and perception has yet to be integrated into practical ASR. ASR can be greatly improved by better integration of structural information with the current stochastic methodology.
自动语音识别(ASR)中最大的问题是鲁棒性——确保ASR模型足够通用。一个强大的ASR系统应该能够在任何合理的环境下解码来自任何说话者的语音。在实践中,除了那些训练过ASR模型的人之外的说话者会导致ASR准确性的显著下降。此外,环境噪声(如天气、其他说话者、汽车)和通信失真(如移动电话)往往会严重降低ASR的性能。即使是简单的麦克风替换也会降低精度。相比之下,人类听众通常可以迅速适应所有这些困难,这强烈表明目前的ASR计划存在重大缺陷。虽然在设计ASR系统时没有必要直接模仿人类的感知,但我们所知道的关于人类语音产生和感知的大部分知识尚未整合到实际的ASR中。通过将结构信息与当前的随机方法更好地结合,可以大大提高ASR。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
OShaughnessy, Douglas其他文献
OShaughnessy, Douglas的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('OShaughnessy, Douglas', 18)}}的其他基金
More efficient and accurate automatic speech recognition
自动语音识别更高效、准确
- 批准号:
RGPIN-2018-05226 - 财政年份:2022
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More efficient and accurate automatic speech recognition
自动语音识别更高效、准确
- 批准号:
RGPIN-2018-05226 - 财政年份:2021
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More efficient and accurate automatic speech recognition
自动语音识别更高效、准确
- 批准号:
RGPIN-2018-05226 - 财政年份:2020
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More efficient and accurate automatic speech recognition
自动语音识别更高效、准确
- 批准号:
RGPIN-2018-05226 - 财政年份:2019
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More efficient and accurate automatic speech recognition
自动语音识别更高效、准确
- 批准号:
RGPIN-2018-05226 - 财政年份:2018
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More Accurate and Efficient Analysis for Automatic Speech Recognition
更准确、更高效的自动语音识别分析
- 批准号:
914-2013 - 财政年份:2017
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More Accurate and Efficient Analysis for Automatic Speech Recognition
更准确、更高效的自动语音识别分析
- 批准号:
914-2013 - 财政年份:2016
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More Accurate and Efficient Analysis for Automatic Speech Recognition
更准确、更高效的自动语音识别分析
- 批准号:
914-2013 - 财政年份:2015
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More Accurate and Efficient Analysis for Automatic Speech Recognition
更准确、更高效的自动语音识别分析
- 批准号:
914-2013 - 财政年份:2014
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
More Accurate and Efficient Analysis for Automatic Speech Recognition
更准确、更高效的自动语音识别分析
- 批准号:
914-2013 - 财政年份:2013
- 资助金额:
$ 3.83万 - 项目类别:
Discovery Grants Program - Individual
相似国自然基金
CBP/p300-HADH轴在基础胰岛素分泌调节中的作用和机制研究
- 批准号:82370798
- 批准年份:2023
- 资助金额:49.00 万元
- 项目类别:面上项目
带有Hamiltonian群作用的横截辛叶状空间的几何与拓扑
- 批准号:11701051
- 批准年份:2017
- 资助金额:22.0 万元
- 项目类别:青年科学基金项目
Basic helix-loop-helix(bHLH)蛋白在光信号以及油菜素甾醇调控拟南芥开花过程中的作用
- 批准号:31200216
- 批准年份:2012
- 资助金额:22.0 万元
- 项目类别:青年科学基金项目
Watanabe块、basic Morita等价与块扩张
- 批准号:10501016
- 批准年份:2005
- 资助金额:14.0 万元
- 项目类别:青年科学基金项目
相似海外基金
Administrative Supplement: Improving Inference of Genetic Architecture and Selection with African Genomes
行政补充:利用非洲基因组改进遗传结构的推断和选择
- 批准号:
10891050 - 财政年份:2023
- 资助金额:
$ 3.83万 - 项目类别:
"Improving Health Equity in Long-Term Care Residents with Dementia: The Role of Race and Ethnicity in Resident-to-Resident Aggression"
“改善患有痴呆症的长期护理居民的健康公平:种族和民族在居民之间的攻击行为中的作用”
- 批准号:
10644715 - 财政年份:2023
- 资助金额:
$ 3.83万 - 项目类别:
Improving Information Sharing Between Family Caregivers and Home Care Aides Caring for Persons Living with ADRD
改善照顾 ADRD 患者的家庭护理人员和家庭护理助理之间的信息共享
- 批准号:
10571144 - 财政年份:2023
- 资助金额:
$ 3.83万 - 项目类别:
Improving Cochlear Implant Outcomes Through Modeling and Programming Strategies Based on Human Inner Ear Pathology
通过基于人类内耳病理学的建模和编程策略改善人工耳蜗的效果
- 批准号:
10825043 - 财政年份:2023
- 资助金额:
$ 3.83万 - 项目类别:
A Conditioned Reinforcement Approach to Improving Self-Control
提高自控力的条件强化方法
- 批准号:
10097938 - 财政年份:2021
- 资助金额:
$ 3.83万 - 项目类别:
A Conditioned Reinforcement Approach to Improving Self-Control
提高自控力的条件强化方法
- 批准号:
10375347 - 财政年份:2021
- 资助金额:
$ 3.83万 - 项目类别:
The BASIC trial: Improving implementation of evidence-based approaches and surveillance to prevent bacterial transmission and infection
BASIC 试验:改进循证方法和监测的实施,以防止细菌传播和感染
- 批准号:
10618922 - 财政年份:2021
- 资助金额:
$ 3.83万 - 项目类别:
The BASIC trial: Improving implementation of evidence-based approaches and surveillance to prevent bacterial transmission and infection
BASIC 试验:改进循证方法和监测的实施,以防止细菌传播和感染
- 批准号:
10316780 - 财政年份:2021
- 资助金额:
$ 3.83万 - 项目类别:
Improving the Accuracy, Utility, and Equity of Risk Assessment in the Juvenile Justice System: A Mixed-Method Study
提高少年司法系统风险评估的准确性、实用性和公平性:混合方法研究
- 批准号:
10301103 - 财政年份:2021
- 资助金额:
$ 3.83万 - 项目类别:
The BASIC trial: Improving implementation of evidence-based approaches and surveillance to prevent bacterial transmission and infection
BASIC 试验:改进循证方法和监测的实施,以防止细菌传播和感染
- 批准号:
10434139 - 财政年份:2021
- 资助金额:
$ 3.83万 - 项目类别: