Deliang Wang

Yufeng Yang, Peidong Wang, DeLiang Wang

This study addresses robust automatic speech recognition (ASR) by introducing a Conformer-based acoustic model. The proposed model builds on the wide residual bi-directional long short-term memory network (WRBN) with utterance-wise dropout and iterative speaker adaptation, but employs a Conformer encoder instead of the recurrent network. The Conformer encoder uses a convolution-augmented attention mechanism for acoustic modeling. The proposed system is evaluated on the monaural ASR task of the CHiME-4 corpus. Coupled with utterance-wise normalization and speaker adaptation, our model achieves $6.25\%$ word error rate, which outperforms WRBN by $8.4\%$ relatively. In addition, the proposed Conformer-based model is $18.3\%$ smaller in model size and reduces total training time by $79.6\%$.

David James Woo, Deliang Wang, Tim Yung et al.

Prompt engineering is critical for effective interaction with large language models (LLMs) such as ChatGPT. However, efforts to teach this skill to students have been limited. This study designed and implemented a prompt engineering intervention, examining its influence on undergraduate students' AI self-efficacy, AI knowledge, and proficiency in creating effective prompts. The intervention involved 27 students who participated in a 100-minute workshop conducted during their history course at a university in Hong Kong. During the workshop, students were introduced to prompt engineering strategies, which they applied to plan the course's final essay task. Multiple data sources were collected, including students' responses to pre- and post-workshop questionnaires, pre- and post-workshop prompt libraries, and written reflections. The study's findings revealed that students demonstrated a higher level of AI self-efficacy, an enhanced understanding of AI concepts, and improved prompt engineering skills because of the intervention. These findings have implications for AI literacy education, as they highlight the importance of prompt engineering training for specific higher education use cases. This is a significant shift from students haphazardly and intuitively learning to engineer prompts. Through prompt engineering education, educators can faciitate students' effective navigation and leverage of LLMs to support their coursework.

Deliang Wang, Chao Yang, Gaowei Chen

Students' academic emotions significantly influence their social behavior and learning performance. Traditional approaches to automatically and accurately analyze these emotions have predominantly relied on supervised machine learning algorithms. However, these models often struggle to generalize across different contexts, necessitating repeated cycles of data collection, annotation, and training. The emergence of Vision-Language Models (VLMs) offers a promising alternative, enabling generalization across visual recognition tasks through zero-shot prompting without requiring fine-tuning. This study investigates the potential of VLMs to analyze students' academic emotions via facial expressions in an online learning environment. We employed two VLMs, Llama-3.2-11B-Vision-Instruct and Qwen2.5-VL-7B-Instruct, to analyze 5,000 images depicting confused, distracted, happy, neutral, and tired expressions using zero-shot prompting. Preliminary results indicate that both models demonstrate moderate performance in academic facial expression recognition, with Qwen2.5-VL-7B-Instruct outperforming Llama-3.2-11B-Vision-Instruct. Notably, both models excel in identifying students' happy emotions but fail to detect distracted behavior. Additionally, Qwen2.5-VL-7B-Instruct exhibits relatively high performance in recognizing students' confused expressions, highlighting its potential for practical applications in identifying content that causes student confusion.

Fan Yu, Shiliang Zhang, Pengcheng Guo et al.

The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants' headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions.

Deliang Wang, Yu Lu, Qinggang Meng et al.

With more deep learning techniques being introduced into the knowledge tracing domain, the interpretability issue of the knowledge tracing models has aroused researchers' attention. Our previous study(Lu et al. 2020) on building and interpreting the KT model mainly adopts the ASSISTment dataset(Feng, Heffernan, and Koedinger 2009),, whose size is relatively small. In this work, we perform the similar tasks but on a large and newly available dataset, called EdNet(Choi et al. 2020). The preliminary experiment results show the effectiveness of the interpreting techniques, while more questions and tasks are worthy to be further explored and accomplished.

Peidong Wang, DeLiang Wang

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes. More specifically, we reduce the floating-point operations in conformer by replacing the transformer module with a performer. The proposed attention-based efficient end-to-end speech recognition model yields competitive performance on the LibriSpeech corpus with 10 millions of parameters and linear computation complexity. The proposed model also outperforms previous lightweight end-to-end models by about 20% relatively in word error rate.

Yu Lu, Deliang Wang, Qinggang Meng et al.

As an important technique for modeling the knowledge states of learners, the traditional knowledge tracing (KT) models have been widely used to support intelligent tutoring systems and MOOC platforms. Driven by the fast advancements of deep learning techniques, deep neural network has been recently adopted to design new KT models for achieving better prediction performance. However, the lack of interpretability of these models has painfully impeded their practical applications, as their outputs and working mechanisms suffer from the intransparent decision process and complex inner structures. We thus propose to adopt the post-hoc method to tackle the interpretability issue for deep learning based knowledge tracing (DLKT) models. Specifically, we focus on applying the layer-wise relevance propagation (LRP) method to interpret RNN-based DLKT model by backpropagating the relevance from the model's output layer to its input layer. The experiment results show the feasibility using the LRP method for interpreting the DLKT model's predictions, and partially validate the computed relevance scores from both question level and concept level. We believe it can be a solid step towards fully interpreting the DLKT models and promote their practical applications in the education domain.

Peidong Wang, Deliang Wang

This paper proposed a class of novel Deep Recurrent Neural Networks which can incorporate language-level information into acoustic models. For simplicity, we named these networks Recurrent Deep Language Networks (RDLNs). Multiple variants of RDLNs were considered, including two kinds of context information, two methods to process the context, and two methods to incorporate the language-level information. RDLNs provided possible methods to fine-tune the whole Automatic Speech Recognition (ASR) system in the acoustic modeling process.

Peidong Wang, Zhongqiu Wang, Deliang Wang

This paper presented our work on applying Recurrent Deep Stacking Networks (RDSNs) to Robust Automatic Speech Recognition (ASR) tasks. In the paper, we also proposed a more efficient yet comparable substitute to RDSN, Bi- Pass Stacking Network (BPSN). The main idea of these two models is to add phoneme-level information into acoustic models, transforming an acoustic model to the combination of an acoustic model and a phoneme-level N-gram model. Experiments showed that RDSN and BPsn can substantially improve the performances over conventional DNNs.