x-vector：Deep Neural Network Embeddings for Text-Independent Speaker Verification
会议：2017 interspeech 机构：The Johns Hopkins University 作者：David Snyder abstract 用dnn提取的embedding取代i-vector表示说话人特征，对输入的speech做时间池化， 用不同长度的语音训练网络，以区别说话人，句子对应定长的embeddding,成对的embedding用于PLDA打分。在NIST SRE201
相关文章
- 1. Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
- 2. 2019--Target Speaker Extraction for Multi-Talker Speaker Verification
- 3. Signature Verification using a Siamese Time Delay Neural Network
- 4. icassp2020--TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES
- 5. Deep Speaker: an End-to-End Neural Speaker Embedding System
- 6. X-VECTOR:ROBUST DNN EMBEDDING FOR SPEAKER RECOGNITION
- 7. Within-sample variability-invariant loss for robust speaker recognition under noisy environments
- 8. (zhuan) Recurrent Neural Network
- 9. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 10. 翻译-Support Vector Machines using GMM Supervectors for Speaker Verification
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • Flink 数据传输及反压详解
- • 算法总结-广度优先算法
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
- 1. 「插件」Runner更新Pro版，帮助设计师远离996
- 2. 错误 707 Could not load file or assembly ‘Newtonsoft.Json, Version=12.0.0.0, Culture=neutral, PublicKe
- 3. Jenkins 2018 报告速览，Kubernetes使用率跃升235%！
- 4. TVI-Android技术篇之注解Annotation
- 5. android studio启动项目
- 6. Android的ADIL
- 7. Android卡顿的检测及优化方法汇总（线下+线上）
- 8. 登录注册的业务逻辑流程梳理
- 9. NDK(1)创建自己的C/C++文件
- 10. 小菜的系统框架界面设计-你的评估是我的决策
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
- 2. 2019--Target Speaker Extraction for Multi-Talker Speaker Verification
- 3. Signature Verification using a Siamese Time Delay Neural Network
- 4. icassp2020--TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES
- 5. Deep Speaker: an End-to-End Neural Speaker Embedding System
- 6. X-VECTOR:ROBUST DNN EMBEDDING FOR SPEAKER RECOGNITION
- 7. Within-sample variability-invariant loss for robust speaker recognition under noisy environments
- 8. (zhuan) Recurrent Neural Network
- 9. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 10. 翻译-Support Vector Machines using GMM Supervectors for Speaker Verification