Difference between revisions of "FreeNeb Status Report 2017-12-11"

From cslt Wiki
Jump to: navigation, search
Line 49: Line 49:
|Zhenlong Han||
|Zhenlong Han||
* Finish training TDNN with different splice and cnn-tdnn model, and give conclusion to xiaohe.
* write document.
* Finish Uyghur model training.
* train some model with 8k and 16k, and add ivector to it.
* English data prepare done.
* English embedded model training.
* English embedded model training.
* Fill in document.

Revision as of 01:47, 11 December 2017

This Week:

People Last Week This Week Next Week Task Tracing(DeadLine)
Mengyuan Zhao
  • Engineering
  1. Bug fix with TTS engine, and release TTS engine v1.0.
  • Engineering
  1. Try to adapt new model TTS model.
Zhiyong Zhang
  • Finished multi-speaker TTS/mono-speaker multi-emotion TTS.
  • Some problems on multi-speaker multi-emotion TTS, need more investigation.
  • To train duration-model using 16k data.
Yang Wei
  • Test FreeNeb TTS engine.
  • Test FreeNeb TTS engine.
Dong Wang
  • Some discussion with Fenyinta
  • Some discussion with Japan Tongfang
  • More people will join!
  • APSIPA 2017

Zhenlong Han
  • write document.
  • train some model with 8k and 16k, and add ivector to it.
  • English embedded model training.
Shuai Zhang
  • Modify the VVParrot project.
  • Complete the VVParrot project.
  • Complete the Megrez project.
  • Add the documents about the two project.

Yanchi Jin
  • Collect a lot of feedback and then update the database of the Megrez.
  • Verify the Megrez_tool and modify the the graph.
  • Complete the Megrez_tool and the chart of structure.
  • Continue update the database.