The offshore environment is complex during automatic target annotation at sea, and the difference between the focal lengths of visible and infrared sensors is large, thereby causing difficulties in matching multitarget electro-optical images at sea. This study proposes a target-matching method for visible and infrared images at sea based on decision-level topological relations. First, YOLOv9 is used to detect targets. To obtain markedly accurate target positions to establish accurate topological relations, the YOLOv9 model is improved for its poor accuracy for small targets, high computational complexity, and difficulty in deployment. To improve the detection accuracy of small targets, an additional small target detection head is added to detect shallow feature maps. From the perspective of reducing network size and achieving lightweight deployment, the Conv module in the model is replaced with DWConv, and the RepNCSPELAN4 module in the backbone network is replaced with the C3Ghost module. The replacements significantly reduce the number of parameters and computation volume of the model while retaining the feature extraction capability of the backbone network. Experimental results of the photovoltaic dataset show that the proposed method improves detection accuracy by 8%, while the computation and number of parameters of the model are reduced by 5.7% and 44.1%, respectively. Lastly, topological relationships are established for the target results, and targets in visible and infrared images are matched based on topological similarity.

To address the triple bottlenecks of data scarcity, oversized models, and slow inference that hinder Cantonese automatic speech recognition (ASR) in low-resource and edge-deployment settings, this study proposes a cost-effective Cantonese ASR system based on LoRA fine-tuning and INT8 quantization. First, Whisper-tiny is parameter-efficiently fine-tuned on the Common Voice zh-HK training set using LoRA with rank = 8. Only 1.6% of the original weights are updated, reducing the character error rate (CER) from 49.5% to 11.1%, a performance close to full fine-tuning (10.3%), while cutting the training memory footprint and computational cost by approximately one order of magnitude. Next, the fine-tuned model is compressed into a 60 MB INT8 checkpoint via dynamic quantization in ONNX Runtime. On a MacBook Pro M1 Max CPU, the quantized model achieves an RTF = 0.20 (offline inference 5 × real-time) and 43% lower latency than the FP16 baseline; on an NVIDIA A10 GPU, it reaches RTF = 0.06, meeting the requirements of high-concurrency cloud services. Ablation studies confirm that the LoRA-INT8 configuration offers the best trade-off among accuracy, speed, and model size. Limitations include the absence of spontaneous-speech noise data, extreme-hardware validation, and adaptive LoRA structure optimization. Future work will incorporate large-scale self-supervised pre-training, tone-aware loss functions, AdaLoRA architecture search, and INT4/NPU quantization, and will establish an mJ/char energy–accuracy curve. The ultimate goal is to achieve CER ≤ 8%, RTF < 0.1, and mJ/char < 1 for low-power real-time Cantonese ASR in practical IoT scenarios.

Cantonese Automatic Speech Recognition (ASR) is hindered by tonal complexity, acoustic diversity, and a lack of labelled data. This study proposes a phoneme-aware hierarchical augmentation framework that enhances performance without additional annotation. A Phoneme Substitution Matrix (PSM), built from Montreal Forced Aligner alignments and Tacotron-2 synthesis, injects adversarial phoneme variants into both transcripts and their aligned audio segments, enlarging pronunciation diversity. Concurrently, a semantic-aware SpecAugment scheme exploits wav2vec 2.0 attention heat maps and keyword boundaries to adaptively mask informative time–frequency regions; a reinforcement-learning controller tunes the masking schedule online, forcing the model to rely on a wider context. On the Common Voice Cantonese 50 h subset, the combined strategy reduces the character error rate (CER) from 26.17% to 16.88% with wav2vec 2.0 and from 38.83% to 23.55% with Zipformer. At 100 h, the CER further drops to 4.27% and 2.32%, yielding relative gains of 32–44%. Ablation studies confirm that phoneme-level and masking components provide complementary benefits. The framework offers a practical, model-independent path toward accurate ASR for Cantonese and other low-resource tonal languages. This paper presents an intelligent sensing-oriented modeling framework for speech signals, which is suitable for deployment on edge or embedded systems to process input from audio sensors (e.g., microphones) and shows promising potential for voice-interactive terminal applications.

With the rapid development of Automatic Speech Recognition (ASR) technology, end-to-end speech recognition systems have gained significant attention due to their ability to directly convert raw speech signals into text. However, such systems heavily rely on large amounts of labeled speech data, which severely limits model training performance and generalization, especially in low-resource language environments. To address this issue, this paper proposes an end-to-end speech recognition approach based on deep fusion, which tightly integrates an external language model (LM) with the end-to-end model during the training phase, effectively compensating for the lack of linguistic prior knowledge. Unlike traditional shallow fusion methods, deep fusion enables the model and the external LM to share representations and jointly optimize during training, thereby enhancing recognition performance under low-resource conditions. Experiments conducted on the Common Voice dataset show that, in a 10 h extremely low-resource scenario, the deep fusion method reduces the character error rate (CER) from 51.1% to 17.65%. In a 100 h scenario, it achieves a relative reduction of approximately 2.8%. Furthermore, ablation studies on model layers demonstrate that even with a reduced number of encoder and decoder layers to decrease model complexity, deep fusion continues to effectively leverage external linguistic priors, significantly improving performance in low-resource speech recognition tasks.

Cantonese automatic speech recognition (ASR) faces persistent challenges due to its nine lexical tones, extensive phonological variation, and the scarcity of professionally transcribed corpora. To address these issues, we propose a lightweight and data-efficient framework that leverages weak phonetic supervision (WPS) in conjunction with two pho-neme-aware augmentation strategies. (1) Dynamic Boundary-Aligned Phoneme Dropout progressively removes entire IPA segments according to a curriculum schedule, simulating real-world phenomena such as elision, lenition, and tonal drift while ensuring training stability. (2) Phoneme-Aware SpecAugment confines all time- and frequency-masking operations within phoneme boundaries and prioritizes high-attention regions, thereby preserving intra-phonemic contours and formant integrity. Built on the Whistle encoder—which integrates a Conformer backbone, Connectionist Temporal Classification–Conditional Random Field (CTC-CRF) alignment, and a multi-lingual phonetic space—the approach requires only a grapheme-to-phoneme lexicon and Montreal Forced Aligner outputs, without any additional manual labeling. Experiments on the Cantonese subset of Common Voice demonstrate consistent gains: Dynamic Dropout alone reduces phoneme error rate (PER) from 17.8% to 16.7% with 50 h of speech and 16.4% to 15.1% with 100 h, while the combination of the two augmentations further lowers PER to 15.9%/14.4%. These results confirm that structure-aware phoneme-level perturbations provide an effective and low-cost solution for building robust Cantonese ASR systems under low-resource conditions.