Due to limited resource on devices and complicated scenarios, a compact model with high precision, low computational cost and latency is expected for small-footprint keyword spotting tasks. To fulfill these requirements, in this paper, compact Feedforward Sequential Memory Network (cFSMN) which combines low-rank matrix factorization with conventional FSMN is investigated for a far-field keyword spotting task. The effect of its architecture parameters is analyzed. Towards achieving lower computational cost, multiframe prediction (MFP) is applied to cFSMN. For enhancing the modeling capacity, an advanced MFP is attempted by inserting small DNN layers before output layers. The performance is measured by area under the curve (AUC) for detection error tradeoff (DET) curves. The experiments show that compared with a well-tuned long short-term memory (LSTM) which needs the same latency and twofold computational cost, the cFSMN achieves 18.11% and 29.21% AUC relative decreases on the test sets which are recorded in quiet and noisy environment respectively. After applying advanced MFP, the system gets 0.48% and 20.04% AUC relative decrease over conventional cFSMN on the quiet and noisy test sets respectively, while the computational cost relatively reduces 46.58%.
The homeostasis of histone methylation is maintained by histone methyltransferases and demethylases, which are important for the regulation of gene expression. Here, we report a histone demethylase from rice (Oryza Sativa), Jumonji C (jmjC) domain containing protein (JMJ710), which belongs to the JMJD6 group and plays an important role in the response to drought stress. Overexpression of JMJ710 causes a drought-sensitive phenotype, while RNAi and CRISPR-knockout mutant lines show drought tolerance. In vitro and in vivo assays showed that JMJ710 is a histone demethylase. It targets to MYB TRANSCRIPTION FACTOR 48 (MYB48-1) chromatin, demethylates H3K36me2, and negatively regulates the expression of MYB48-1, a positive regulator of drought tolerance. Under drought stress, JMJ710 is downregulated and the expression of MYB48-1 increases, and the subsequent activation of its downstream drought-responsive genes leads to drought tolerance. This research reports a negative regulator of drought stress-responsive genes, JMJ710, that ensures that the drought tolerance mechanism is not mis-activated under normal conditions but allows quick activation upon drought stress.
The recurrent neural network transducer (RNN-T) model has been proved effective for keyword spotting (KWS) recently. However, compared with cross-entropy (CE) or connectionist temporal classification (CTC) based models, the additional prediction network in the RNN-T model increases the model size and computational cost. Besides, since the keyword training data usually only contain the keyword sequence, the prediction network might has over-fitting problems. In this paper, we improve the RNN-T modeling for small-footprint keyword spotting in three aspects. First, to address the overfitting issue, we explore multi-task training where a CTC loss is added to the encoder. The CTC loss is calculated with both KWS data and ASR data, while the RNN-T loss is calculated with ASR data so that only the encoder is augmented with KWS data. Second, we use the feed-forward neural network to replace the LSTM for prediction network modeling. Thus all possible prediction network outputs could be pre-computed for decoding. Third, we further improve the model with transfer learning, where a model trained with 160 thousand hours of ASR data is used to initialize the KWS model. On a self-collected far-field wake-word testset, the proposed RNN-T system greatly improves the performance comparing with a strong "keyword-filler" baseline.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.