2013-05-17

Data sharing

• LM count files still undelivered!

DNN progress

Experiments

• setups for input layer

s1: mfcc(13), splice +-5[143]

s2: mfcc(13), splice +-5(143), LDA[143]

s3: mfcc(13), delta(39), splice +-5(429), LDA[143]

s4: mfcc(13), delta(39), splice +-5(429), LDA[300]

• setups for alignment

tri1: triphone training, feature input: mfcc(13), delta[39]. #pdfs 1651, #gaussians 10028

tri2: LDA/MLLT training, feature input: mfcc(13), delta(39), splice +-4(351), LDA[40]. #pdfs 3536, #gaussians 39995

• other notes

about 100 hours training data

88k LM, biglm decoding (1e-5 / 1e-9)

gpu-based nnet training, in-1200-1200-1200-1200-out

• results

Test Set	fMMI	s1/tri1	s2/tri1	s3/tri1	s4/tri1	s2/tri2	s4/tri2	cpu-based (like s4/tri1)
map	28.58	25.38	24.47	26.16	26.20	22.85	24.27	26.45
2044	24.79	23.58	22.82	23.84	24.13	21.45	22.76	24.66
notetp3	21.64	16.08	14.89	15.92	15.97	14.89	14.79	16.14
1900	8.19	8.55	8.43	8.66	8.90	7.30	7.91	8.23
general	39.63	36.18	34.79	35.88	35.90	33.06	33.79	38.02
online1	35.19	34.68	33.90	33.45	33.38	32.93	32.43	33.00
online2	28.30	27.27	26.61	26.26	26.36	25.94	25.69	26.63
speedup	28.45	24.97	24.40	24.55	25.42	23.04	23.67	27.17

• conclusion

1. the GPU approach is comparable with the CPU approach (see s4/tri1 & CPU results). The former works slightly better in most cases.
2. the fine training leads to significant better performance than the rough training (see s2/tri1 vs s2/tri2 & s4/tri1 vs s4/tri2)
3. the delta features do not help, actually harm the perfromance (see s2/tri1 vs s3/tri1 & s4/tri1)
4. the identical-dimension LDA helps the performance (see s1/tri1 vs s2/tri1)

the best system is s2/tri2: without delta, apply a linear LDA.

• to be done

1. experiment with Tencent feature
2. migrate the bottlenck structure to the 100k task with s2/tri2.

Tencent exps

1. 手动将NN网络的W权重，较小的置零，在保留30%左右的较大权重的条件下，系统性能未见明显衰减。
2. 按照HTK模型的结构，以及HTK align的结构，修改Kaldi的GPU接口，验证并无问题，已开始较大规模数据训练（1000小时），网络结构前后5帧扩展，4个隐层，每层2048节点，输出15000个状态。使用mpe模型alignment，特征为plp特征，未做任何映射。
3. 解码器仍在CLG结构下，修改声学模型计算接口，接入DNN模型，验证无问题，已开始效率优化。

待做实验：

1. 验证不同学习率调节策略，指数下降衰减方式，newbob方式。
2. 验证不同特征在大数据上的作用。
3. 最后层不过softmax，降维得到BN特征实验，类似IBM BN做法

GPU & CPU merge

1. just started

L-1 sparse initial training

• experiments on L1 and L2 penalty

1. LM: 4G gigabyte LM, 1e-5 small LM
2. AM: 100hour tri4b_nn

Test Set	0	1.00E-06	1.00E-05	2.50E-05	5.00E-05	7.50E-05	1.00E-04
map	61.06	61.18	61.31	61.72	62.89	62.84	62.48
2044	49.53	49.58	49.84	49.94	50.71	51.08	51.08
notetp3	43.44	43.44	43.55	44.58	45.22	44.95	45.76
1900	38.50	38.54	39.00	39.21	40.33	40.53	40.60
general	61.24	61.22	61.69	61.84	62.71	62.83	62.93
online1	58.02	58.05	58.31	58.23	58.83	59.06	59.46
online2	53.62	53.70	54.03	53.93	54.65	54.94	55.51
speedup	57.51	57.49	57.93	58.31	59.75	60.08	59.52

• Conclusions

1. L1 and L2 penalty do not work in the current nnet-GPU code.
2. will work to check the L1 code and change the penalty scheme.

Kaldi/HTK merge

• HTK2Kaldi: hold.
• Kaldi2HTK: stuck. various sp models tried but don't help
• Need thorough debug this week.

Embedded progress

• Status:

1. first embedded demo done, 1000 words take 3.2M memory.
2. accuracy test not yet finished
3. training acoustic model for sphinx. The toolkit runs well, need prepare data and start parallel training.

• To be done

1. finish AM training
2. run offline test