Traditional fault detection methods for batch process based on data-driven often need to make assumptions about the distribution of process data, and often lead to false positives and false negatives when dealing with non-linear data and other complex data. To solve this problem, a supervised learning algorithm based on Long Short-Term Memory (LSTM) network and Batch Normalization (BN) was proposed, which does not need to make assumptions about the distribution of original data. Firstly, a preprocessing method based on variable-wise unfolding and continuous sampling was applied to the batch process raw data, so that the processed data could be input to the LSTM unit. Then, the improved deep LSTM network was used for feature learning. By adding the BN layer and the representation method of cross entropy loss, the network was able to effectively extract the characteristics of the batch process data and learned quickly. Finally, a simulation experiment was performed on a semiconductor etching process. The experimental results show that compared with Multilinear Principal Component Analysis (MPCA) method, the proposed method can identify more faults types, which can effectively identify various faults, and the overall detection rate of faults reaches more than 95%. Compared with the traditional single-LSTM model, it has higher recognition speed, and its overall detection rate of faults is increased by more than 8%, and it is suitable for dealing with fault detection problems with non-linear and multi-case characteristics in the batch process.

The parameter distribution of unvoiced/voiced Line Spectrum Frequency (LSF) has differences. In order to improve the quantization performance of LSF parameters in vocoder, an unvoiced/voiced mode codebook design algorithm based on Cell Evenness (CE) was presented by using the difference between unvoiced/voiced LSF parameters distribution and CE. Firstly, the optimal amount ratio of unvoiced/voiced LSF parameters participating in the codebook training was deduced according to CE. Then the specified number of atypia LSF parameters were eliminated from unvoiced speech. The final codebook was retrained. The experimental results show that, compared with the shared codebook algorithm under the same bit-rate condition, the average spectrum distortion of the proposed algorithm was reduced by 2.5%, the mean opinion score was increased by 2.3% and the storage of codebook was reduced by 21.1%. The proposed algorithm is also adapted to the vocoder without unvoiced/voiced symbol transmission and the algorithm is also adapted to the vocoder without unvoiced/voiced symbol transmission.