“2014-01-03”版本间的差异

2014年1月3日 (五) 02:20的最后版本

AM development

Sparse DNN

• Optimal Brain Damage(OBD).

1. Online OBD held.
2. OBD + L1 norm start to investigation.

• Efficient computing

1. Conducting rearrangement the matrix structure and compose zero blocks by some smart approaches, leading to better computing speed.

Efficient DNN training

1. L1-L2 grid checking: L1/L2(< 1e-6) seems good for record1900 but worse for other test sets.

link here

1. Asymmetric window: Great improvement on training set(WER 34% to 24%), however the improvement is lost on test. Overfitting?
2. Frame-skipping. Skipping 1 frame speeds up decoding in a consistent way while retaining the accuracy largely. Skipping more frames lead to unacceptable performance degradation.
3. Interpolation does not provide performance gain.

link here

Optimal phoneset

• Analyze Tencent English phone set. Found some errors in CH/EN phone sharing.
• Develop a new sharing scheme, start training the new system.
• Start training for all-separated phones
• Start training mixed system with Chinglish data.

Engine optimization

• Investigating LOUDS FST. On progress.

LM development

NN LM

• Collecting a bigger lexicon: 40k words related to music, 56k words from an official dictionary.
• Working on NN LM based on word2vector.

Embedded development

• Liuchao's cellphone, Qualcomm Snapdragon Krait MSM8960 @ 1.5GHz, using 1 core

small nnet 100/600/600/600/600/1264 with MFCC input

• 4500 words:

• construct LG: 0.41s
• compose HCLG with det: 13.70s, 5.318 MB
• compose HCLG without det: 6.61s, 5.488 MB

• 950 words:

• construct LG: 0.15s
• compose HCLG with det: 2.63s, 0.947 MB, decode RT 0.649
• compose HCLG without det: 1.74s, 0.998 MB, decode RT 0.548

• For word list or simple grammars, determinization leads to small RT increase, but can improve HCLG compiling dramatically. This is particularly the case for embedded devices.
• The accuracy does not change with/without determinization.

Speech QA

• Use N-best to expand match in QA. Better performance were obtained.

• 1-best matches 96/121
• 10-best matches 102/121

• Use N-best to recover errors in entity check. Working on.
• Use Pinyin to recover errors in entity check. Future work.