“Active Projects”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第1行: 第1行:
 
=Active projects=
 
=Active projects=
  
[[Auio-Visual Speech Processing (NSFC 62171250)]]
+
*[[Auio-Visual Speech Processing (NSFC 62171250)]]
 
+
*[http://lilt.cslt.org/trials/demo/ On the Evaluation Trials in Speaker Verification]
[http://lilt.cslt.org/trials/demo/ On the Evaluation Trials in Speaker Verification]
+
*[[AI Graph]]
 
+
 
+
 
+
[[AI Graph]]
+
  
 
=Paused projects=
 
=Paused projects=
  
[[Vivi-poem-generation|Vivi Poem]]
+
*[[Vivi-poem-generation|Vivi Poem]]
  
 
=Completed projects=
 
=Completed projects=
  
[http://lipq.cslt.org/cam Reliable Visualization for Deep Speaker Recognition (Interspeech 22)]
+
*[http://lipq.cslt.org/cam Reliable Visualization for Deep Speaker Recognition (Interspeech 22)]
[http://cycleflow.cslt.org CycleFlow (Odyssey 22)]
+
*[http://cycleflow.cslt.org CycleFlow (Odyssey 22)]
[http://rc.cslt.org Random Cycle Loss and Its Application to Speaker Recognition (PAMI)]
+
*[http://rc.cslt.org Random Cycle Loss and Its Application to Speaker Recognition (PAMI)]
  
 
[[AI 100 QA]]
 
[[AI 100 QA]]

2023年6月2日 (五) 05:56的版本

Active projects

Paused projects

Completed projects

AI 100 QA

Speech Processing

Enhanced exemplar autoencoder with cycle consistency loss in any-to-one voice conversion (OCOCOSDA 22)

Deep Speech Factorization (Phase 2)

Multilingual Minorilanguage Automatic Speech Recognition (M2ASR)

Deep Generative Factorization For Speech Signal(ICASSP21)

Unsupervised speech factorization (ICASSP20)

CN-Celeb (ICASSP20)

Deep Speaker Feature Learning

Deep Speech Factorization (Phase I)

Speaker Recognition on Trivial Events

Phonetic Temporal Neural Model for Language Identification

Deep speaker segmentation

Flexible speech synthesis

M2ASR (NSFC project)

Language Processing

Vivi Neural translation

Financial Processing

Risk Aversion Corn-K