There are two basic problems in sign language recognition (SLR): (a) isolated word SLR and (b) continuous SLR. Most of the existing continuous SLR methods are extensions of the isolated word SLR methods. These methods use the isolated word SLR results as the basic module and obtain the sentence recognition results through sentence segmentation and word alignment. However, sentence segmentation and word alignment are often not accurate, resulting in a low sentence recognition accuracy. At the same time, continuous SLR usually requires strict sample labels, leading to the difficult task of manual labeling and limited training data availability. To address these challenges, this paper proposes a bidirectional spatial–temporal LSTM fusion attention network (Bi-ST-LSTM-A) for continuous SLR. This approach avoids problems such as sentence segmentation, word alignment, and tedious manual labeling. Our contributions are summarized as follows: (1) we proposed a sign language video feature representation method using a convolutional neural network (CNN) and spatial–temporal LSTM (ST-LSTM) information fusion technology; and (2) we constructed a uniform neural machine translation framework that can be used for complex continuous SLR and gesture recognition of nonspecific people in nonspecific environments. Experiments were carried out on some large continuous sign language datasets. The sign language recognition accuracy reached 81.22% on the 500 CSL dataset, 76.12% on the RWTH-PHOENIX-Weather dataset and 75.32% on the RWTH-PHOENIX-Weather-2014T dataset, thereby illustrating the effectiveness of the proposed framework.

A novel multimodal fusion approach is proposed for Chinese sign language (CSL) recognition. This framework, the LSTM2+CHMM model, uses dual long short-term memory (LSTM) and a couple hidden Markov model (CHMM) to fuse hand and skeleton sequence information. Novel contributions include: (1) a unique hand segmentation algorithm using power rate transforms and RGB-D image fusion. This approach effectively overcomes common limitations such as complex backgrounds, inconsistent lighting, and variable skin tones. (2) As a result, the proposed skeleton-hand fusion framework can be used for vision-based sign language recognition (SLR) of non-specific people in non-specific environments. (3) This LSTM2+CHMM model combines probability theory with a neural network to provide a unified methodology for multiple-sequence fusion. The proposed SLR framework was tested using two CSL datasets and experimental results showed it to be effective.

A dual-band balanced-to-balanced (BTB) filtering power divider (FPD) is presented, which can achieve an in-phase power division with high selectivity. The proposed FPD is composed of microstrip-to-slotline transition structures (MTSTSs), T-shaped slotline, and multiple stub-loaded resonators (SLRs). A dual-band differential-mode (DM) response with a steep filtering performance is generated by employing SLRs. By adjusting the electrical lengths of SLRs and the gaps between each resonator and microstrip lines, the fractional bandwidth (FBW) is controllable. By introducing slotline resonators loaded with surface-mounted resistors, the isolation between the two output ports is increased. Meanwhile, a wide DM stopband with a high rejection level is obtained. Moreover, good wideband common-mode (CM) suppression is achieved intrinsically, thereby simplifying the design procedure greatly. To verify the theoretical prediction, one FPD prototype is fabricated. A good agreement between the simulated and measured results is observed. To the best of authors' knowledge, the proposed dual-band BTB FPD is first ever reported.