arXiv subjects

Hang Chen

Publications and source records attributed to Hang Chen.

At least 73 records · Page 4Linked to original sources

arXiv2024

Learning a Structural Causal Model for Intuition Reasoning in Conversation

Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component of it, remains largely unexplored due to the absence of a well-designed cognitive model. In this paper, inspired by intuition theory on conversation cognition, we develop a conversation cognitive model (CCM) that explains how each utterance receives and activates channels of information recursively. Besides, we algebraically transformed CCM into a structural causal model (SCM) under some mild assumptions, rendering it compatible with various causal discovery methods. We further propose a probabilistic implementation of the SCM for utterance-level relation reasoning. By leveraging variational inference, it explores substitutes for implicit causes, addresses the issue of their unobservability, and reconstructs the causal representations of utterances through the evidence lower bounds. Moreover, we constructed synthetic and simulated datasets incorporating implicit causes and complete cause labels, alleviating the current situation where all available datasets are implicit-causes-agnostic. Extensive experiments demonstrate that our proposed method significantly outperforms existing methods on synthetic, simulated, and real-world datasets. Finally, we analyze the performance of CCM under latent confounders and propose theoretical ideas for addressing this currently unresolved issue.

cs.CL↗

arXiv2023

A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations

The fusion of causal models with deep learning introducing increasingly intricate data sets, such as the causal associations within images or between textual components, has surfaced as a focal research area. Nonetheless, the broadening of original causal concepts and theories to such complex, non-statistical data has been met with serious challenges. In response, our study proposes redefinitions of causal data into three distinct categories from the standpoint of causal structure and representation: definite data, semi-definite data, and indefinite data. Definite data chiefly pertains to statistical data used in conventional causal scenarios, while semi-definite data refers to a spectrum of data formats germane to deep learning, including time-series, images, text, and others. Indefinite data is an emergent research sphere inferred from the progression of data forms by us. To comprehensively present these three data paradigms, we elaborate on their formal definitions, differences manifested in datasets, resolution pathways, and development of research. We summarize key tasks and achievements pertaining to definite and semi-definite data from myriad research undertakings, present a roadmap for indefinite data, beginning with its current research conundrums. Lastly, we classify and scrutinize the key datasets presently utilized within these three paradigms.

cs.LG↗

arXiv2023

How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning

Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language models (LLMs), excel at capturing semantic correlations within utterance embeddings but fall short in determining the specific causal relationships. To overcome this limitation, we propose the incorporation of \textit{i.i.d.} noise terms into the conversation process, thereby constructing a structural causal model (SCM). It explores how distinct causal relationships of fitted embeddings can be discerned through independent conditions. To facilitate the implementation of deep learning, we introduce the cogn frameworks to handle unstructured conversation data, and employ an autoencoder architecture to regard the unobservable noise as learnable "implicit causes." Moreover, we curate a synthetic dataset that includes i.i.d. noise. Through comprehensive experiments, we validate the effectiveness and interpretability of our approach. Our code is available in https://github.com/Zodiark-ch/mater-of-our-EMNLP2023-paper.

cs.CL↗

arXiv2023

The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge

This technical report details our submission system to the CHiME-7 DASR Challenge, which focuses on speaker diarization and speech recognition under complex multi-speaker scenarios. Additionally, it also evaluates the efficiency of systems in handling diverse array devices. To address these issues, we implemented an end-to-end speaker diarization system and introduced a rectification strategy based on multi-channel spatial information. This approach significantly diminished the word error rates (WER). In terms of recognition, we utilized publicly available pre-trained models as the foundational models to train our end-to-end speech recognition models. Our system attained a Macro-averaged diarization-attributed WER (DA-WER) of 21.01% on the CHiME-7 evaluation set, which signifies a relative improvement of 62.04% over the official baseline system.

eess.AS↗

arXiv2023

The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction

Previous Multimodal Information based Speech Processing (MISP) challenges mainly focused on audio-visual speech recognition (AVSR) with commendable success. However, the most advanced back-end recognition systems often hit performance limits due to the complex acoustic environments. This has prompted a shift in focus towards the Audio-Visual Target Speaker Extraction (AVTSE) task for the MISP 2023 challenge in ICASSP 2024 Signal Processing Grand Challenges. Unlike existing audio-visual speech enhance-ment challenges primarily focused on simulation data, the MISP 2023 challenge uniquely explores how front-end speech processing, combined with visual clues, impacts back-end tasks in real-world scenarios. This pioneering effort aims to set the first benchmark for the AVTSE task, offering fresh insights into enhancing the ac-curacy of back-end speech recognition systems through AVTSE in challenging and real acoustic environments. This paper delivers a thorough overview of the task setting, dataset, and baseline system of the MISP 2023 challenge. It also includes an in-depth analysis of the challenges participants may encounter. The experimental results highlight the demanding nature of this task, and we look forward to the innovative solutions participants will bring forward.

eess.AS↗

arXiv2023

Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023

In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. In our framework, deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion. Then, we introduce a joint decoding structure for emotion classification and valence regression in the decoding stage. A multi-task loss based on uncertainty is also designed to optimize the whole process. Finally, by combining three different structures on the posterior probability level, we obtain the final predictions of discrete and dimensional emotions. When tested on the dataset of multimodal emotion recognition challenge (MER 2023), the proposed framework yields consistent improvements in both emotion classification and valence regression. Our final system achieves state-of-the-art performance and ranks third on the leaderboard on MER-MULTI sub-challenge.

eess.AS↗

arXiv2023

Towards Causal Representation Learning and Deconfounding from Indefinite Data

Owing to the cross-pollination between causal discovery and deep learning, non-statistical data (e.g., images, text, etc.) encounters significant conflicts in terms of properties and methods with traditional causal data. To unify these data types of varying forms, we redefine causal data from two novel perspectives and then propose three data paradigms. Among them, the indefinite data (like dialogues or video sources) induce low sample utilization and incapability of the distribution assumption, both leading to the fact that learning causal representation from indefinite data is, as of yet, largely unexplored. We design the causal strength variational model to settle down these two problems. Specifically, we leverage the causal strength instead of independent noise as the latent variable to construct evidence lower bound. By this design ethos, The causal strengths of different structures are regarded as a distribution and can be expressed as a 2D matrix. Moreover, considering the latent confounders, we disentangle the causal graph G into two relation subgraphs O and C. O contains pure relations between observed variables, while C represents the relations from latent variables to observed variables. We implement the above designs as a dynamic variational inference model, tailored to learn causal representation from indefinite data under latent confounding. Finally, we conduct comprehensive experiments on synthetic and real-world data to demonstrate the effectiveness of our method.

cs.LG↗

arXiv2023

Semi-supervised multi-channel speaker diarization with cross-channel attention

Most neural speaker diarization systems rely on sufficient manual training data labels, which are hard to collect under real-world scenarios. This paper proposes a semi-supervised speaker diarization system to utilize large-scale multi-channel training data by generating pseudo-labels for unlabeled data. Furthermore, we introduce cross-channel attention into the Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding (NSD-MA-MSE) to learn channel contextual information of speaker embeddings better. Experimental results on the CHiME-7 Mixer6 dataset which only contains partial speakers' labels of the training set, show that our system achieved 57.01% relative DER reduction compared to the clustering-based model on the development set. We further conducted experiments on the CHiME-6 dataset to simulate the scenario of missing partial training set labels. When using 80% and 50% labeled training data, our system performs comparably to the results obtained using 100% labeled data for training.

eess.AS↗

arXiv2023

BFRT: Blockchained Federated Learning for Real-time Traffic Flow Prediction

Accurate real-time traffic flow prediction can be leveraged to relieve traffic congestion and associated negative impacts. The existing centralized deep learning methodologies have demonstrated high prediction accuracy, but suffer from privacy concerns due to the sensitive nature of transportation data. Moreover, the emerging literature on traffic prediction by distributed learning approaches, including federated learning, primarily focuses on offline learning. This paper proposes BFRT, a blockchained federated learning architecture for online traffic flow prediction using real-time data and edge computing. The proposed approach provides privacy for the underlying data, while enabling decentralized model training in real-time at the Internet of Vehicles edge. We federate GRU and LSTM models and conduct extensive experiments with dynamically collected arterial traffic data shards. We prototype the proposed permissioned blockchain network on Hyperledger Fabric and perform extensive tests using virtual machines to simulate the edge nodes. Experimental results outperform the centralized models, highlighting the feasibility of our approach for facilitating privacy-preserving and decentralized real-time traffic flow prediction.

cs.DC↗

arXiv2023

Reilly-type inequalities for submanifolds in Cartan-Hadamard manifolds

Let $M$ be an $m (\ge2)$-dimensional closed orientable submanifold in an $n$-dimensional complete simply-connected Riemannian manifold $N$, where the sectional curvature of $N$ is bounded above by $δ$. When $δ<0$, inspired by Niu-Xu (arXiv:2106.01912), we give new upper bounds for the first nonzero eigenvalues of the $p$-Laplacian and the $L_T$ operator, respectively. These generalize Niu-Xu's work for the Laplacian (arXiv:2106.01912) and improve the estimates due to Chen (Nonlinear Anal.,196, 111833, 2020) for the $p$-Laplacian and Grosjean (Hokkaido Math. J., 33(2) , 319-339, 2004) for the $L_T$ operator, respectively. We also obtain several Reilly-type inequalities for the weighted manifolds and some boundary value problems.

math.DG↗

arXiv2023

Rigidity of $k$-extremal submanifolds in a sphere

In this paper, we study the rigidity of $k(\ge 1)$-extremal submanifolds in a sphere and prove various pinching theorems under different curvature conditions, including sectional and Ricci curvatures in pointwise and integral sense.

math.DG↗

arXiv2023

The Multimodal Information based Speech Processing (MISP) 2022 Challenge: Audio-Visual Diarization and Recognition

The Multi-modal Information based Speech Processing (MISP) challenge aims to extend the application of signal processing technology in specific scenarios by promoting the research into wake-up words, speaker diarization, speech recognition, and other technologies. The MISP2022 challenge has two tracks: 1) audio-visual speaker diarization (AVSD), aiming to solve ``who spoken when'' using both audio and visual data; 2) a novel audio-visual diarization and recognition (AVDR) task that focuses on addressing ``who spoken what when'' with audio-visual speaker diarization results. Both tracks focus on the Chinese language, and use far-field audio and video in real home-tv scenarios: 2-6 people communicating each other with TV noise in the background. This paper introduces the dataset, track settings, and baselines of the MISP2022 challenge. Our analyses of experiments and examples indicate the good performance of AVDR baseline system, and the potential difficulties in this challenge due to, e.g., the far-field video quality, the presence of TV noise in the background, and the indistinguishable speakers.

cs.MM↗

arXiv2022

Dual adaptive training of photonic neural networks

Photonic neural network (PNN) is a remarkable analog artificial intelligence (AI) accelerator that computes with photons instead of electrons to feature low latency, high energy efficiency, and high parallelism. However, the existing training approaches cannot address the extensive accumulation of systematic errors in large-scale PNNs, resulting in a significant decrease in model performance in physical systems. Here, we propose dual adaptive training (DAT) that allows the PNN model to adapt to substantial systematic errors and preserves its performance during the deployment. By introducing the systematic error prediction networks with task-similarity joint optimization, DAT achieves the high similarity mapping between the PNN numerical models and physical systems and high-accurate gradient calculations during the dual backpropagation training. We validated the effectiveness of DAT by using diffractive PNNs and interference-based PNNs on image classification tasks. DAT successfully trained large-scale PNNs under major systematic errors and preserved the model classification accuracies comparable to error-free systems. The results further demonstrated its superior performance over the state-of-the-art in situ training approaches. DAT provides critical support for constructing large-scale PNNs to achieve advanced architectures and can be generalized to other types of AI systems with analog computing errors.

cs.LG↗

arXiv2022

Progressive Multi-Scale Self-Supervised Learning for Speech Recognition

Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning theoretically. To this end, we propose a progressive multi-scale self-supervised learning (PMS-SSL) method, which uses fine-grained target sets to compute SSL loss at top layer while uses coarse-grained target sets at intermediate layers. Furthermore, PMS-SSL introduces multi-scale structure into multi-head self-attention for better speech representation, which restricts the attention area into a large scope at higher layers while restricts the attention area into a small scope at lower layers. Experiments on Librispeech dataset indicate the effectiveness of our proposed method. Compared with HuBERT, PMS-SSL achieves 13.7% / 12.7% relative WER reduction on test other evaluation subsets respectively when fine-tuned on 10hours / 100hours subsets.

eess.AS↗

arXiv2022

Improved Speech Pre-Training with Supervision-Enhanced Acoustic Unit

Speech pre-training has shown great success in learning useful and general latent representations from large-scale unlabeled data. Based on a well-designed self-supervised learning pattern, pre-trained models can be used to serve lots of downstream speech tasks such as automatic speech recognition. In order to take full advantage of the labed data in low resource task, we present an improved pre-training method by introducing a supervision-enhanced acoustic unit (SEAU) pattern to intensify the expression of comtext information and ruduce the training cost. Encoder representations extracted from the SEAU pattern are used to generate more representative target units for HuBERT pre-training process. The proposed method, named SeHuBERT, achieves a relative word error rate reductions of 10.5% and 4.9% comared with the standard HuBERT on Turkmen speech recognition task with 500 hours and 100 hours fine-tuning data respectively. Extended to more languages and more data, SeHuBERT can aslo achieve a relative word error rate reductions of approximately 10% at half of the training cost compared with HuBERT.

eess.AS↗

arXiv2022

Optical multi-task learning using multi-wavelength diffractive deep neural networks

Photonic neural networks are brain-inspired information processing technology using photons instead of electrons to perform artificial intelligence (AI) tasks. However, existing architectures are designed for a single task but fail to multiplex different tasks in parallel within a single monolithic system due to the task competition that deteriorates the model performance. This paper proposes a novel optical multi-task learning system by designing multi-wavelength diffractive deep neural networks (D2NNs) with the joint optimization method. By encoding multi-task inputs into multi-wavelength channels, the system can increase the computing throughput and significantly alle-viate the competition to perform multiple tasks in parallel with high accuracy. We design the two-task and four-task D2NNs with two and four spectral channels, respectively, for classifying different inputs from MNIST, FMNIST, KMNIST, and EMNIST databases. The numerical evaluations demonstrate that, under the same network size, mul-ti-wavelength D2NNs achieve significantly higher classification accuracies for multi-task learning than single-wavelength D2NNs. Furthermore, by increasing the network size, the multi-wavelength D2NNs for simultaneously performing multiple tasks achieve comparable classification accuracies with respect to the individual training of multiple single-wavelength D2NNs to perform tasks separately. Our work paves the way for developing the wave-length-division multiplexing technology to achieve high-throughput neuromorphic photonic computing and more general AI systems to perform multiple tasks in parallel.

cs.LG↗

arXiv2022

Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function

In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function. We first collect a data set for multi-modal sound source localization (SSL) where both audio and visual signals are recorded in real-life home TV scenarios. Then we propose a novel spatial annotation method to produce the ground truth of DOA for each speaker with the video data by transformation between camera coordinate and pixel coordinate according to the pin-hole camera model. With spatial location information served as another input along with acoustic feature, multi-speaker DOA estimation could be solved as a classification task of active speaker detection. Label permutation problem in multi-speaker related tasks will be addressed since the locations of each speaker are used as input. Experiments conducted on both simulated data and real data show that the proposed audio-visual DOA estimation model outperforms audio-only DOA estimation model by a large margin.

eess.AS↗

arXiv2022

Optical Neural Ordinary Differential Equations

Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance. However, the successively cascading of network hidden layers results in larger integrated photonic chip areas. To address this issue, we propose the optical neural ordinary differential equations (ON-ODE) architecture that parameterizes the continuous dynamics of hidden layers with optical ODE solvers. The ON-ODE comprises the PNNs followed by the photonic integrator and optical feedback loop, which can be configured to represent residual neural networks (ResNet) and recurrent neural networks with effectively reduced chip area occupancy. For the interference-based optoelectronic nonlinear hidden layer, the numerical experiments demonstrate that the single hidden layer ON-ODE can achieve approximately the same accuracy as the two-layer optical ResNet in image classification tasks. Besides, the ONODE improves the model classification accuracy for the diffraction-based all-optical linear hidden layer. The time-dependent dynamics property of ON-ODE is further applied for trajectory prediction with high accuracy.

cs.LG↗