“ASR Status Report 2017-7-10”版本间的差异

• Finish the test website with Tanghui

• Read the paper of Paralinguistics
• Make a plan for recording and start to record hopefully.

• help zheling to finish his first crawler program
• chech hazak speech data
  • train: 1346 utterances' WER large than 20% (utterance level WER)
  • test: 759 utterances' WER large than 20%(utterance level WER)

• tools for speech data checking
• transfer learning based on large Chinese ASR model

• Scanned the source code of auto-scoring system;
• A report about the research of the speech group (Thursday).

• Replace the old version kaldi with new ones.
• Gather Part 1: 'Speech, Speech Processing and Tools' of Kaldi book for further release.

• prepared for the report
• did translation

• do a report
• finish the website
• comfirm the next work direction with Tanghui and yixiang

• submitted the technical report
• finished to check the subset(happy) of our speech database
• test the model of detecting overlapped speech

here

• check the subset(angry) of our database
• finish the website with zhangmiao and yixiang

• use dnn & sigmoid to prune result

• Importance of each layer; try Tanh.

• kazak ASR transfor learning
• help zheling Zhang to learn Scrapy

• finish kazak ASR　transfor learning
• help zheling Zhang to write his first Web crawler

• absent.

• write book.
• check the process of deep speaker segmentation.
• demo for speech synthesis.

• deep speaker visulization and segmentation.

• Compile auto-scoring system;
• Chinglish for mix-asr training.

• A report about the research of the speech group (Thursday);
• Into the source code of auto-scoring system;