Arrow Research search

Author name cluster

Deliang Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers
1 author row

Possible papers

9

AAAI Conference 2025 Short Paper

Extended LSTMs for Knowledge Tracing: Peeking Inside the Black Box (Student Abstract)

  • Deliang Wang
  • Yu Lu
  • Gaowei Chen

This paper proposes extended Long Short-Term Memory (LSTM) networks for the knowledge tracing task and employs explainable AI methods to address interpretability issues. Specifically, we developed an extended LSTM-based model to automatically diagnose students' knowledge states. We then leveraged three interpreting methods—gradient sensitivity, gradient*input, and Deep SHAP—to explain the model's predictions by computing input contributions. The results demonstrate that the proposed model outperforms DKT, and the three methods effectively explain its predictions. Additionally, we identified three key insights into the model's working mechanisms.

PDF Details DOI

AAAI Conference 2024 Short Paper

Opening the Black Box: Unraveling the Classroom Dialogue Analysis (Student Abstract)

  • Deliang Wang

This paper explores proposing interpreting methods from explainable artificial intelligence to address the interpretability issues in deep learning-based models for classroom dialogue. Specifically, we developed a Bert-based model to automatically detect student talk moves within classroom dialogues, utilizing the TalkMoves dataset. Subsequently, we proposed three generic interpreting methods, namely saliency, input*gradient, and integrated gradient, to explain the predictions of classroom dialogue models by computing input relevance (i.e., contribution). The experimental results show that the three interpreting methods can effectively unravel the classroom dialogue analysis, thereby potentially fostering teachers' trust.

PDF Details DOI

NeurIPS Conference 2012 Conference Paper

Cocktail Party Processing via Structured Prediction

  • Yuxuan Wang
  • Deliang Wang

While human listeners excel at selectively attending to a conversation in a cocktail party, machine performance is still far inferior by comparison. We show that the cocktail party problem, or the speech separation problem, can be effectively approached via structured prediction. To account for temporal dynamics in speech, we employ conditional random fields (CRFs) to classify speech dominance within each time-frequency unit for a sound mixture. To capture complex, nonlinear relationship between input and output, both state and transition feature functions in CRFs are learned by deep neural networks. The formulation of the problem as classification allows us to directly optimize a measure that is well correlated with human speech intelligibility. The proposed system substantially outperforms existing ones in a variety of noises.

PDF Details

NeurIPS Conference 2002 Conference Paper

Monaural Speech Separation

  • Guoning Hu
  • Deliang Wang

that deals with Monaural speech separation has been studied in previous systems that incorporate auditory scene analysis principles. A major problem for these systems is their inability to deal with speech in the high- frequency range. Psychoacoustic evidence suggests that different perceptual mechanisms are involved in handling resolved and unresolved harmonics. Motivated by this, we propose a model for monaural separation low-frequency and high- frequency signals differently. For resolved harmonics, our model generates segments based on temporal continuity and cross-channel correlation, and groups them according to periodicity. For unresolved harmonics, the model generates segments based on amplitude modulation (AM) in addition to temporal continuity and groups them according to AM repetition rates derived from sinusoidal modeling. Underlying the separation process is a pitch contour obtained according to psychoacoustic constraints. Our model is systematically evaluated, and it yields substantially better performance than previous systems, especially in the high-frequency range.

PDF Details

NeurIPS Conference 1999 Conference Paper

An Oscillatory Correlation Frame work for Computational Auditory Scene Analysis

  • Guy Brown
  • Deliang Wang

A neural model is described which uses oscillatory correlation to segregate speech from interfering sound sources. The core of the model is a two-layer neural oscillator network. A sound stream is represented by a synchronized population of oscillators, and different streams are represented by desynchronized oscillator populations. The model has been evaluated using a corpus of speech mixed with interfering sounds, and produces an improvement in signal-to-noise ratio for every mixture.

PDF Details

NeurIPS Conference 1999 Conference Paper

Perceptual Organization Based on Temporal Dynamics

  • Xiuwen Liu
  • Deliang Wang

A figure-ground segregation network is proposed based on a novel boundary pair representation. Nodes in the network are bound(cid: 173) ary segments obtained through local grouping. Each node is ex(cid: 173) citatorily coupled with the neighboring nodes that belong to the same region, and inhibitorily coupled with the corresponding paired node. Gestalt grouping rules are incorporated by modulating con(cid: 173) nections. The status of a node represents its probability being figural and is updated according to a differential equation. The system solves the figure-ground segregation problem through tem(cid: 173) poral evolution. Different perceptual phenomena, such as modal and amodal completion, virtual contours, grouping and shape de(cid: 173) composition are then explained through local diffusion. The system eliminates combinatorial optimization and accounts for many psy(cid: 173) chophysical results with a fixed set of parameters.

PDF Details

NeurIPS Conference 1998 Conference Paper

Perceiving without Learning: From Spirals to Inside/Outside Relations

  • Ke Chen
  • Deliang Wang

As a benchmark task, the spiral problem is well known in neural net(cid: 173) works. Unlike previous work that emphasizes learning, we approach the problem from a generic perspective that does not involve learning. We point out that the spiral problem is intrinsically connected to the in(cid: 173) side/outside problem. A generic solution to both problems is proposed based on oscillatory correlation using a time delay network. Our simu(cid: 173) lation results are qualitatively consistent with human performance, and we interpret human limitations in terms of synchrony and time delays, both biologically plausible. As a special case, our network without time delays can always distinguish these figures regardless of shape, position, size, and orientation.

PDF Details

NeurIPS Conference 1994 Conference Paper

Synchrony and Desynchrony in Neural Oscillator Networks

  • Deliang Wang
  • David Terman

An novel class of locally excitatory, globally inhibitory oscillator networks is proposed. The model of each oscillator corresponds to a standard relaxation oscillator with two time scales. The network exhibits a mechanism of selective gating, whereby an oscillator jumping up to its active phase rapidly recruits the oscillators stimulated by the same pattern, while preventing others from jumping up. We show analytically that with the selective gating mechanism the network rapidly achieves both synchronization within blocks of oscillators that are stimulated by connected regions and desynchronization between different blocks. Computer simulations demonstrate the network's promising ability for segmenting multiple input patterns in real time. This model lays a physical foundation for the oscillatory correlation theory of feature binding, and may provide an effective computational framework for scene segmentation and figure/ground segregation.

PDF Details
v2026.09.13