Fei Chen

Tianyang Hu, Fei Chen, Haonan Wang et al.

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of the latent space is empirically pivotal, determining the optimal choice and the process of identifying it remain unclear. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity. Our investigation starts with the classic generative adversarial networks (GANs). Inspired by the GAN training objective, we propose a novel "distance" between the latent and data distributions, whose minimization coincides with that of the generator complexity. The minimizer of this distance is characterized as the optimal data-dependent latent that most effectively capitalizes on the generator's capacity. Then, we consider parameterizing such a latent distribution by an encoder network and propose a two-stage training strategy called Decoupled Autoencoder (DAE), where the encoder is only updated in the first stage with an auxiliary decoder and then frozen in the second stage while the actual decoder is being trained. DAE can improve the latent distribution and as a result, improve the generative performance. Our theoretical analyses are corroborated by comprehensive experiments on various models such as VQGAN and Diffusion Transformer, where our modifications yield significant improvements in sample quality with decreased model complexity.

Ryandhimas E. Zezario, Fei Chen, Chiou-Shann Fuh et al.

Improving the user's hearing ability to understand speech in noisy environments is critical to the development of hearing aid (HA) devices. For this, it is important to derive a metric that can fairly predict speech intelligibility for HA users. A straightforward approach is to conduct a subjective listening test and use the test results as an evaluation metric. However, conducting large-scale listening tests is time-consuming and expensive. Therefore, several evaluation metrics were derived as surrogates for subjective listening test results. In this study, we propose a multi-branched speech intelligibility prediction model (MBI-Net), for predicting the subjective intelligibility scores of HA users. MBI-Net consists of two branches of models, with each branch consisting of a hearing loss model, a cross-domain feature extraction module, and a speech intelligibility prediction model, to process speech signals from one channel. The outputs of the two branches are fused through a linear layer to obtain predicted speech intelligibility scores. Experimental results confirm the effectiveness of MBI-Net, which produces higher prediction scores than the baseline system in Track 1 and Track 2 on the Clarity Prediction Challenge 2022 dataset.

Ryandhimas E. Zezario, Fei Chen, Chiou-Shann Fuh et al.

Automated speech intelligibility assessment is pivotal for hearing aid (HA) development. In this paper, we present three novel methods to improve intelligibility prediction accuracy and introduce MBI-Net+, an enhanced version of MBI-Net, the top-performing system in the 1st Clarity Prediction Challenge. MBI-Net+ leverages Whisper's embeddings to create cross-domain acoustic features and includes metadata from speech signals by using a classifier that distinguishes different enhancement methods. Furthermore, MBI-Net+ integrates the hearing-aid speech perception index (HASPI) as a supplementary metric into the objective function to further boost prediction performance. Experimental results demonstrate that MBI-Net+ surpasses several intrusive baseline systems and MBI-Net on the Clarity Prediction Challenge 2023 dataset, validating the effectiveness of incorporating Whisper embeddings, speech metadata, and related complementary metrics to improve prediction performance for HA.

Yong Feng, Fei Chen, Jiasong Wu

A new Lp-norm constraint least mean square (Lp-LMS) algorithm with new strategy of varying p is presented, which is applied to system identification in this letter. The parameter p is iteratively adjusted by the gradient method applied to the root relative deviation of the estimated weight vector. Numerical simulations show that this new algorithm achieves lower steady-state error as well as equally fast convergence compared with the traditional Lp-LMS and LMS algorithms in the application setting of sparse system identification in the presence of noise.

Yue Meng, Fei Chen, Chuchu Fan

Learning control policies for complex, long-horizon tasks is a central challenge in robotics and autonomous systems. Signal Temporal Logic (STL) offers a powerful and expressive language for specifying such tasks, but its non-Markovian nature and inherent sparse reward make it difficult to be solved via standard Reinforcement Learning (RL) algorithms. Prior RL approaches focus only on limited STL fragments or use STL robustness scores as sparse terminal rewards. In this paper, we propose TGPO, Temporal Grounded Policy Optimization, to solve general STL tasks. TGPO decomposes STL into timed subgoals and invariant constraints and provides a hierarchical framework to tackle the problem. The high-level component of TGPO proposes concrete time allocations for these subgoals, and the low-level time-conditioned policy learns to achieve the sequenced subgoals using a dense, stage-wise reward signal. During inference, we sample various time allocations and select the most promising assignment for the policy network to rollout the solution trajectory. To foster efficient policy learning for complex STL with multiple subgoals, we leverage the learned critic to guide the high-level temporal search via Metropolis-Hastings sampling, focusing exploration on temporally feasible solutions. We conduct experiments on five environments, ranging from low-dimensional navigation to manipulation, drone, and quadrupedal locomotion. Under a wide range of STL tasks, TGPO significantly outperforms state-of-the-art baselines (especially for high-dimensional and long-horizon cases), with an average of 31.6% improvement in task success rate compared to the best baseline. The code will be available at https://github.com/mengyuest/TGPO

Shuchen Xue, Zhaoqiang Liu, Fei Chen et al.

Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization problem that seeks more appropriate time steps for a specific numerical ODE solver for DPMs. This optimization problem aims to minimize the distance between the ground-truth solution to the ODE and an approximate solution corresponding to the numerical solver. It can be efficiently solved using the constrained trust region method, taking less than $15$ seconds. Our extensive experiments on both unconditional and conditional sampling using pixel- and latent-space DPMs demonstrate that, when combined with the state-of-the-art sampling method UniPC, our optimized time steps significantly improve image generation performance in terms of FID scores for datasets such as CIFAR-10 and ImageNet, compared to using uniform time steps.

Petru-Daniel Tudosiu, Yongxin Yang, Shifeng Zhang et al.

Text-to-image generation has achieved astonishing results, yet precise spatial controllability and prompt fidelity remain highly challenging. This limitation is typically addressed through cumbersome prompt engineering, scene layout conditioning, or image editing techniques which often require hand drawn masks. Nonetheless, pre-existing works struggle to take advantage of the natural instance-level compositionality of scenes due to the typically flat nature of rasterized RGB output images. Towards adressing this challenge, we introduce MuLAn: a novel dataset comprising over 44K MUlti-Layer ANnotations of RGB images as multilayer, instance-wise RGBA decompositions, and over 100K instance images. To build MuLAn, we developed a training free pipeline which decomposes a monocular RGB image into a stack of RGBA layers comprising of background and isolated instances. We achieve this through the use of pretrained general-purpose models, and by developing three modules: image decomposition for instance discovery and extraction, instance completion to reconstruct occluded areas, and image re-assembly. We use our pipeline to create MuLAn-COCO and MuLAn-LAION datasets, which contain a variety of image decompositions in terms of style, composition and complexity. With MuLAn, we provide the first photorealistic resource providing instance decomposition and occlusion information for high quality images, opening up new avenues for text-to-image generative AI research. With this, we aim to encourage the development of novel generation and editing technology, in particular layer-wise solutions. MuLAn data resources are available at https://MuLAn-dataset.github.io/.

Junjia Liu, Zhuo Li, Minghao Yu et al.

Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor. However, learning these skills is challenging due to the high degrees of freedom of humanoid robots, and collecting sufficient training data for humanoid is a laborious process. Given the rapid introduction of new humanoid platforms, a cross-embodiment framework that allows generalizable skill transfer is becoming increasingly critical. To address this, we propose a transferable framework that reduces the data bottleneck by using a unified digital human model as a common prototype and bypassing the need for re-training on every new robot platform. The model learns behavior primitives from human demonstrations through adversarial imitation, and the complex robot structures are decomposed into functional components, each trained independently and dynamically coordinated. Task generalization is achieved through a human-object interaction graph, and skills are transferred to different robots via embodiment-specific kinematic motion retargeting and dynamic fine-tuning. Our framework is validated on five humanoid robots with diverse configurations, demonstrating stable loco-manipulation and highlighting its effectiveness in reducing data requirements and increasing the efficiency of skill transfer across platforms.

Yuting Ding, Fei Chen

Auditory spatial attention detection (ASAD) is used to determine the direction of a listener's attention to a speaker by analyzing her/his electroencephalographic (EEG) signals. This study aimed to further improve the performance of ASAD with a short decision window (i.e., <1 s) rather than with long decision windows ranging from 1 to 5 seconds in previous studies. An end-to-end temporal attention network (i.e., TAnet) was introduced in this work. TAnet employs a multi-head attention (MHA) mechanism, which can more effectively capture the interactions among time steps in collected EEG signals and efficiently assign corresponding weights to those EEG time steps. Experiments demonstrated that, compared with the CNN-based method and recent ASAD methods, TAnet provided improved decoding performance in the KUL dataset, with decoding accuracies of 92.4% (decision window 0.1 s), 94.9% (0.25 s), 95.1% (0.3 s), 95.4% (0.4 s), and 95.5% (0.5 s) with short decision windows (i.e., <1 s). As a new ASAD model with a short decision window, TAnet can potentially facilitate the design of EEG-controlled intelligent hearing aids and sound recognition systems.

Yuanming Zhang, Jing Lu, Fei Chen et al.

Decoding the directional focus of an attended speaker from listeners' electroencephalogram (EEG) signals is essential for developing brain-computer interfaces to improve the quality of life for individuals with hearing impairment. Previous works have concentrated on binary directional focus decoding, i.e., determining whether the attended speaker is on the left or right side of the listener. However, a more precise decoding of the exact direction of the attended speaker is necessary for effective speech processing. Additionally, audio spatial information has not been effectively leveraged, resulting in suboptimal decoding results. In this paper, it is found that on the recently presented dataset with 14-class directional focus, models relying exclusively on EEG inputs exhibit significantly lower accuracy when decoding the directional focus in both leave-one-subject-out and leave-one-trial-out scenarios. By integrating audio spatial spectra with EEG features, the decoding accuracy can be effectively improved. The CNN, LSM-CNN, and Deformer models are employed to decode the directional focus from listeners' EEG signals and audio spatial spectra. The proposed Sp-EEG-Deformer model achieves notable 14-class decoding accuracies of 55.35% and 57.19% in leave-one-subject-out and leave-one-trial-out scenarios with a decision window of 1 second, respectively. Experiment results indicate increased decoding accuracy as the number of alternative directions reduces. These findings suggest the efficacy of our proposed dual modal directional focus decoding strategy.

Gesa Mittmann, Sara Laiouar-Pedari, Hendrik A. Mehrtens et al.

The aggressiveness of prostate cancer, the most common cancer in men worldwide, is primarily assessed based on histopathological data using the Gleason scoring system. While artificial intelligence (AI) has shown promise in accurately predicting Gleason scores, these predictions often lack inherent explainability, potentially leading to distrust in human-machine interactions. To address this issue, we introduce a novel dataset of 1,015 tissue microarray core images, annotated by an international group of 54 pathologists. The annotations provide detailed localized pattern descriptions for Gleason grading in line with international guidelines. Utilizing this dataset, we develop an inherently explainable AI system based on a U-Net architecture that provides predictions leveraging pathologists' terminology. This approach circumvents post-hoc explainability methods while maintaining or exceeding the performance of methods trained directly for Gleason pattern segmentation (Dice score: 0.713 $\pm$ 0.003 trained on explanations vs. 0.691 $\pm$ 0.010 trained on Gleason patterns). By employing soft labels during training, we capture the intrinsic uncertainty in the data, yielding strong results in Gleason pattern segmentation even in the context of high interobserver variability. With the release of this dataset, we aim to encourage further research into segmentation in medical tasks with high levels of subjectivity and to advance the understanding of pathologists' reasoning processes.

Ryandhimas E. Zezario, Szu-Wei Fu, Fei Chen et al.

In this study, we propose a cross-domain multi-objective speech assessment model called MOSA-Net, which can estimate multiple speech assessment metrics simultaneously. Experimental results show that MOSA-Net can improve the linear correlation coefficient (LCC) by 0.026 (0.990 vs 0.964 in seen noise environments) and 0.012 (0.969 vs 0.957 in unseen noise environments) in perceptual evaluation of speech quality (PESQ) prediction, compared to Quality-Net, an existing single-task model for PESQ prediction, and improve LCC by 0.021 (0.985 vs 0.964 in seen noise environments) and 0.047 (0.836 vs 0.789 in unseen noise environments) in short-time objective intelligibility (STOI) prediction, compared to STOI-Net (based on CRNN), an existing single-task model for STOI prediction. Moreover, MOSA-Net, originally trained to assess objective scores, can be used as a pre-trained model to be effectively adapted to an assessment model for predicting subjective quality and intelligibility scores with a limited amount of training data. Experimental results show that MOSA-Net can improve LCC by 0.018 (0.805 vs 0.787) in mean opinion score (MOS) prediction, compared to MOS-SSL, a strong single-task model for MOS prediction. In light of the confirmed prediction capability, we further adopt the latent representations of MOSA-Net to guide the speech enhancement (SE) process and derive a quality-intelligibility (QI)-aware SE (QIA-SE) approach accordingly. Experimental results show that QIA-SE provides superior enhancement performance compared with the baseline SE system in terms of objective evaluation metrics and qualitative evaluation test. For example, QIA-SE can improve PESQ by 0.301 (2.953 vs 2.652 in seen noise environments) and 0.18 (2.658 vs 2.478 in unseen noise environments) over a CNN-based baseline SE model.

Sunny Katyara, Nikhil Deshpande, Fanny Ficuciello et al.

Handling non-rigid objects using robot hands necessities a framework that does not only incorporate human-level dexterity and cognition but also the multi-sensory information and system dynamics for robust and fine interactions. In this research, our previously developed kernelized synergies framework, inspired from human behaviour on reusing same subspace for grasping and manipulation, is augmented with visuo-tactile perception for autonomous and flexible adaptation to unknown objects. To detect objects and estimate their poses, a simplified visual pipeline using RANSAC algorithm with Euclidean clustering and SVM classifier is exploited. To modulate interaction efforts while grasping and manipulating non-rigid objects, the tactile feedback using T40S shokac chip sensor, generating 3D force information, is incorporated. Moreover, different kernel functions are examined in the kernelized synergies framework, to evaluate its performance and potential against task reproducibility, execution, generalization and synergistic re-usability. Experiments performed with robot arm-hand system validates the capability and usability of upgraded framework on stably grasping and dexterously manipulating the non-rigid objects.

Sara Akbarzadeh, Sungmin Lee, Fei Chen et al.

Electrical hearing by cochlear implants (CIs) may be fundamentally different from acoustic hearing by normal-hearing (NH) listeners, presumably showing unequal speech quality perception in various noise environments. Noise reduction (NR) algorithms used in CI reduce the noise in favor of signal-to-noise ratio (SNR), regardless of plausible accompanying distortions that may degrade the speech quality perception. To gain better understanding of CI speech quality perception, the present work aimed investigating speech quality perception in a diverse noise conditions, including factors of speech/noise levels, type of noise, and distortions caused by NR models. Fifteen NH and seven CI subjects participated in this study. Speech sentences were set to two different levels (65 and 75 dB SPL). Two types of noise (Cafeteria and Babble) at three levels (55, 65, and 75 dB SPL) were used. Sentences were processed using two NR algorithms to investigate the perceptual sensitivity of CI and NH listeners to the distortion. All sentences processed with the combinations of these sets were presented to CI and NH listeners, and they were asked to rate the sound quality of speech as they perceived. The effect of each factor on the perceived speech quality was investigated based on the group averaged quality rated by CI and NH listeners. Consistent with previous studies, CI listeners were not as sensitive as NH to the distortion made by NR algorithms. Statistical analysis showed that the speech level has significant effect on quality perception. At the same SNR, the quality of 65 dB speech was rated higher than that of 75 dB for CI users, but vice versa for NH listeners. Therefore, the present study showed that the perceived speech quality patterns were different between CI and NH listeners in terms of their sensitivity to distortion and speech level in complex listening environment.

Wei-Jen Lee, Syu-Siang Wang, Fei Chen et al.

Reverberation, which is generally caused by sound reflections from walls, ceilings, and floors, can result in severe performance degradation of acoustic applications. Due to a complicated combination of attenuation and time-delay effects, the reverberation property is difficult to characterize, and it remains a challenging task to effectively retrieve the anechoic speech signals from reverberation ones. In the present study, we proposed a novel integrated deep and ensemble learning algorithm (IDEA) for speech dereverberation. The IDEA consists of offline and online phases. In the offline phase, we train multiple dereverberation models, each aiming to precisely dereverb speech signals in a particular acoustic environment; then a unified fusion function is estimated that aims to integrate the information of multiple dereverberation models. In the online phase, an input utterance is first processed by each of the dereverberation models. The outputs of all models are integrated accordingly to generate the final anechoic signal. We evaluated the IDEA on designed acoustic environments, including both matched and mismatched conditions of the training and testing data. Experimental results confirm that the proposed IDEA outperforms single deep-neural-network-based dereverberation model with the same model architecture and training data.

Yong Feng, Fei Chen, Rui Zeng et al.

Sparse adaptive filtering has gained much attention due to its wide applicability in the field of signal processing. Among the main algorithm families, sparse norm constraint adaptive filters develop rapidly in recent years. However, when applied for system identification, most priori work in sparse norm constraint adaptive filtering suffers from the difficulty of adaptability to the sparsity of the systems to be identified. To address this problem, we propose a novel variable p-norm constraint least mean square (LMS) algorithm, which serves as a variant of the conventional Lp-LMS algorithm established for sparse system identification. The parameter p is iteratively adjusted by the gradient descent method applied to the instantaneous square error. Numerical simulations show that this new approach achieves better performance than the traditional Lp-LMS and LMS algorithms in terms of steady-state error and convergence rate.