2013年11月29日 (五) 04:00的最后版本

ASR

ASR Kernel development

[ASR group weekly report]

TTS

• This week

• 5000 utterance training done.
• 500 utterance TN recording done. Quality control is not very good. Resulting synthesis is not satisfied.
• 41 WD utterance recording. Quality control fine. Adaptation done. Sounds OK.
• Buzzy sound was investigated.The main source is the source model (excitation). STRAIGHT sounds better.

• Next week

• Developing CGI service.
• Prepare to 2000 utt female record.

Dialog system

Statistical approach

• HowNET information extracted. Coverage is limited. 50k words.
• Custom task error analysis

There are totally 2000 errors. Investigated into 600 errors.

• NULL query, 1.4%
• English upper/lower mismatch. 1.6%
• Traditional/Simple Chinese mismatch. 2.2%
• High frequency of sub-important words, like taxing. 1.3%
• Database labeling error (matched query is better than the labeled correct query). 21.8%
• Stand query or query involve many unimportant words, leading to less TF/IDF. STOP words still impact. 10.7%
• TF/IDF incorrectly weighted the matched terms. 3.9%
• Synonym can not match. 36.5%
• Category words can not match. 13.5%
• Answer label incorrect. Semantic relationship missing. 6.8%
• Word segmentation hide keywords. 4%
• Vague query. None discriminative words after stop words purging. 1.6%

Template matching

• Work on disambiguousness
• Completed the prototype design for the QA logic
• Develop an assistant tool for source code generation