Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency

Connectionist Temporal Classification (CTC), a non-autoregressive training criterion, is widely used in online keyword spotting (KWS). However, existing CTC-based KWS decoding strategies either rely on Automatic Speech Recognition (ASR), which performs suboptimally due to its broad search over the acoustic space without keyword-specific optimization, or on KWS-specific decoding graphs, which are complex to implement and maintain. In this work, we propose a streaming decoding algorithm enhanced by Cross-layer Discrimination Consistency (CDC), tailored for CTC-based KWS. Specifically, we introduce a streamlined yet effective decoding algorithm capable of detecting the start of the keyword at any arbitrary position. Furthermore, we leverage discrimination consistency information across layers to better differentiate between positive and false alarm samples. Our experiments on both clean and noisy Hey Snips datasets show that the proposed streaming decoding strategy outperforms ASR-based and graph-based KWS baselines. The CDC-boosted decoding further improves performance, yielding an average absolute recall improvement of 6.8% and a 46.3% relative reduction in the miss rate compared to the graph-based KWS baseline, with a very low false alarm rate of 0.05 per hour.

Color image segmentation based on a convex K-means approach

Image segmentation is a fundamental and challenging task in image processing and computer vision. The color image segmentation is attracting more attention due to the color image provides more information than the gray image. In this paper, we propose a variational model based on a convex K-means approach to segment color images. The proposed variational method uses a combination of $l_1$ and $l_2$ regularizers to maintain edge information of objects in images while overcoming the staircase effect. Meanwhile, our one-stage strategy is an improved version based on the smoothing and thresholding strategy, which contributes to improving the accuracy of segmentation. The proposed method performs the following steps. First, we specify the color set which can be determined by human or the K-means method. Second, we use a variational model to obtain the most appropriate color for each pixel from the color set via convex relaxation and lifting. The Chambolle-Pock algorithm and simplex projection are applied to solve the variational model effectively. Experimental results and comparison analysis demonstrate the effectiveness and robustness of our method.