Speaker Representations
From i-vectors to end to end systems
Deepu Vijayasenan
National Institute of Technology, Karnataka
声纹识别PPT....
需积分: 9 83 浏览量
2022-04-21
01:54:24
上传
评论
收藏 40.53MB ZIP 举报
声纹识别.zip （46个子文件） 
声纹识别 
DrDeepu_WiSSAP2019.pdf 1.82MB
声纹识别.pptx 5.95MB
d-vector.bmp 2MB speaker_2.bmp 44KB PPT_image 
Verification_system_overview.png 55KB speaker_recognition_bak.png 375KB bottleneck_feature_2.png 37KB speaker_verification_system.png 208KB
framework.jpg 83KB speaker_recognition.png 288KB
“自动恢复”保存声纹识别.docx 13.06MB i-vectors-in-detail.png 333KB speaker_recognition_2.png 262KB speech_speaker_recognition.png 146KB speech_introduction.png 119KB speaker_1.bmp 44KB speaker_identification_2.bmp 36KB 声纹识别.docx 16.87MB speaker_identification_3.bmp 33KB d-vector_2.bmp 1.87MB Example-of-speech-signal-time-domain.png 51KB speaker.jpg 58KB ~$声纹识别.docx 162B verification.jpg 68KB equation.bmp 19KB speaker_verification_system.png 200KB x-vector.bmp 2.39MB listener.bmp 497KB 2018_icassp_xvectors.pdf 190KB i-vectors-in-detail.png 327KB framework.bmp 2.2MB d-vector.jpg 57KB 1111.bmp 2.69MB x-vector.jpg 100KB bans_icon_1.bmp 17KB x-vector-embeding.bmp 1.49MB speaker_identification_4.bmp 69KB bans_icon_2.bmp 15KB speaker_diaration.png 34KB speech_speaker_recognition.png 162KB d-vector_2.jpg 82KB speaker.png 21KB speech_introduction.png 119KB speaker.bmp 530KB speaker_identification_1.bmp 207KB Bottleneck_Feature.bmp 2.16MB
评论0