Advances in SVM-Based System Using GMM Super Vectors for Text-Independent Speaker Verification

来源 :Tsinghua Science and Technology | 被引量 : 0次 | 上传用户:wuww
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
For text-independent speaker verification, the Gaussian mixture model (GMM) using a universal background model strategy and the GMM using support vector machines are the two most commonly used methodologies. Recently, a new SVM-based speaker verification method using GMM super vectors has been proposed. This paper describes the construction of a new speaker verification system and investigates the use of nuisance attribute projection and test normalization to further enhance performance. Experiments were conducted on the core test of the 2006 NIST speaker recognition evaluation corpus. The experimental results indicate that an SVM-based speaker verification system using GMM super vectors can achieve ap-pealing performance. With the use of nuisance attribute projection and test normalization, the system per-formance can be significantly improved, with improvements in the equal error rate from 7.78% to 4.92% and detection cost function from 0.0376 to 0.0251. For text-independent speaker verification, the Gaussian mixture model (GMM) using a universal background model strategy and the GMM using support vector machines are the two most commonly used methodologies. Recently, a new SVM-based speaker verification method using GMM super vectors has been proposed. This paper describes the construction of a new speaker verification system and investigates the use of nuisance attribute projection and test normalization to further enhance performance. Experiments were conducted on the core test of the 2006 NIST speaker recognition evaluation corpus. that an SVM-based speaker verification system using GMM super vectors can achieve ap-pealing performance. With the use of nuisance attribute projection and test normalization, the system per-formance can be significantly improved, with improvements in the equal error rate from 7.78% to 4.92% and detection cost function from 0.0376 to 0.0251.
其他文献
目的:观察在产妇分娩护理中,助产士温馨护理的实际效果.方法:纳入我院2019年1—11月期间妇产科收治的102例分娩产妇为对象,将其随机均匀分成对照组(51例)和实验组(51例),对照
初中阶段是学生培养学习习惯的关键阶段,学生一旦学会独立思考,养成独立思考的能力将对学生今后的发展学习有很大的助益。尤其是数学学科,由于数学本身具有很好的逻辑思维能
新课程改革的背景下,学生的主体地位有了显著的提高,教师在教育教学中,更加注重引导学生自主学习,组织学生快乐学习.单纯的灌输,只会使学生机械地记忆,严重剥夺学生的学习主
目的:探讨新生儿肺炎的护理效果及核心要点.方法:收集2017年1月至2017年12月在我院进行肺炎治疗的新生儿72例,按照随机法分成实验组和参照组.实验组采取优质护理干预,参照组
目的:观察不孕不育患者采用宫腔镜下输卵管插管通液治疗的效果.方法:选取2017年7月~2018年8月收治的不孕不育患者62例,随机数字表法分为观察组和对照组各 31 例,对照组采取常
做好种子的处理——温汤浸种:黄瓜黑星病带菌的种子可用54℃的温水浸种15分钟,捞出后再放清水中浸泡4~6小时,即可消灭病菌。又例如:西红柿在育苗前,把种子浸入50℃温水中浸泡3
小学数学是初中数学的基础,所以从小培养学生学习数学的能力势在必行.教师要在有限的时间里培养学生学习数学的能力,就必须找准途径,提高学生学习数学的兴趣,增强学生学好数
好的教育,不会强求人为实现某个单一的目标而压制甚至牺牲个体的需求,而是尊重生命的自然需求,让每一只小鸟唱自己的歌!坚持以人为本,坚持以学生发展为本,其根本目标就是要落
目的:探讨伽玛刀立体定向放射治疗中小型听神经瘤的效果.方法:随机将我院2014年1月至2017年12月收治的150例中小型听神经瘤患者分为两组,常规显微外科组75例给予常规显微外科
目的:研究临床上利用针对性护理对连续性血液净化患儿并发症的影响.方法:选取我院连续性血液净化患儿72例作为研究对象,均分为观察组与对照组各36例,其中对照组采用常规护理,