34 accepted papers
Existing neural vocoders have demonstrated promising performance by leveraging Mel-spectrum as an acoustic feature for conditional audio generation. Nonetheless, they remain constrained by an inherent ``performance-cost
In the field of audio generation, signal-to-noise ratio (SNR) has long served as an objective metric for evaluating audio quality. Nevertheless, recent studies have shown that SNR and its variants are not always highly correlated with human perception, prompting us to raise the questions: Why does
Although lip-to-speech synthesis (L2S) has achieved significant progress in recent years, current state-of-the-art methods typically rely on intermediate representations such as mel-spectrograms or discrete self-supervised learning (SSL) tokens. The potential of latent diffusion models (LDMs) in thi
Dynamically Reconfigurable Battery (DRB) systems employ power electronic switches to create dynamic topologies. They enable effective management of cell difference through real-time adjustment of cell connections. However, existing DRB control methods struggle to learn effective strategies due to sp
Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes, but directly sharing them poses privacy risks. A common defense involves per-example l_2 clipping before prototype computation to bound sensitivity, followe
Conversational Tabular Data Analysis, a collaboration between humans and machines, enables real-time data exploration for informed decision-making. The challenges and costs of collecting realistic conversational logs for tabular data analysis hinder comprehensive quantitative evaluation of Large Lan…
Wide dynamic range compression (WDRC) provides level-dependent amplification, intended to make the output of a hearing aid fall between the hearing threshold and the highest comfortable level of the listener. Hearing aids often combine noise reduction with WDRC, applied sequentially. Unfortunately,…
Recent advancements in large language models (LLMs) have significantly improved the performance of multi-hop question answering (MHQA) systems. Despite the success of MHQA systems, the evaluation of MHQA is not deeply investigated. Existing evaluations mainly focus on comparing the final answers of…
Target speaker extraction (TSE) aims to directly extract the desired speech given enrollment utterances of the target speaker. Despite significant progress in recent years, most existing methods remain non-causal and computationally intensive. This paper introduces DSINet, a real-time time-frequency…
Hearing assistive devices aim to compensate hearing loss for hearing-impaired listeners, and their maximum stable gain (MSG) is constrained because of the existence of the acoustic feedback between the receiver and microphone, resulting in their inefficiency for individuals with severe or profound h…
Comprehensible neural network explanations are foundations for a better understanding of decisions, especially when the input data are infused with malicious perturbations. Existing solutions generally mitigate the impact of perturbations through adversarial training, yet they fail to generate compr…
Graph neural networks (GNNs) leverage message passing mechanisms to learn the topological features of graph data. Traditional GNNs learns node features in a spatial domain unrelated to the topology, which can hardly ensure topological features. In this paper, we formulates message passing as a syste…
Despite the rapid development of neural vocoders in recent years, they usually suffer from some intrinsic challenges like opaque modeling, and parameter-performance trade-off. In this study, we propose an innovative time-frequency (T-F) domain-based neural vocoder to resolve the above-mentioned chal
Detecting driver fatigue is critical for road safety, as drowsy driving remains a leading cause of traffic accidents. Many existing solutions rely on computationally demanding deep learning models, which result in high latency and are unsuitable for embedded robotic devices with limited resources (s
Open-world planning poses a significant challenge for general artificial intelligence due to environmental complexity and task diversity, especially in long-term tasks and lifelong learning. Inspired by cognitive theories, we propose M2PA, an open-world multi-memory planning agent. M2PA innovates by…
The challenge of developing agents capable of open-world planning remains fundamental to artificial general intelligence (AGI). While large language models (LLMs) have made progress with their vast world knowledge, their limitations in perception, memory, and reliable reasoning still hinder LLM-base…
Retrieval-Augmented Generation (RAG) systems commonly suffer from **Knowledge Conflicts**, where retrieved external knowledge contradicts the inherent, parametric knowledge of large language models (LLMs). It adversely affects performance on downstream tasks such as question answering (QA). Existing…
The Dynamically Reconfigurable Battery (DRB) systems, which use high-speed power electronic switches to dynamically adjust battery interconnections in real-time, are critical to the performance of the battery pack. Traditional battery management strategies often fail to address multi-objective optim
Despite the abundance of prior social strategies possessed by humans, there remains a paucity of research dedicated to their transfer and integration into social agents. Our proposed SOTOPIA-Ω framework aims to address and bridge this gap, with a particular focus on enhancing the social capabilities…
We investigate how to select the number of communities for weighted networks without a full likelihood modeling. First, we propose a novel weighted degree-corrected stochastic block model (DCSBM), where the mean adjacency matrix is modeled in the same way as in the standard DCSBM, while the variance…
Multi-view clustering (MVC) aims to integrate complementary information from multiple views to enhance clustering performance. Late Fusion Multi-View Clustering (LFMVC) has shown promise by synthesizing diverse clustering results into a unified consensus. However, current LFMVC methods struggle with…
Column generation (CG) is a well-established method for solving large-scale linear programs. It involves iteratively optimizing a subproblem containing a subset of columns and using its dual solution to generate new columns with negative reduced costs. This process continues until the dual values co…
Existing frame-wise neural beamformers for speech extraction can obtain promising performance in relatively high signal-to-noise ratio (SNR) scenarios using small microphone arrays, while they still suffer from performance degradation in relatively low SNR environments, e.g., SNR<-5 dB. As an attemp…
In domestic environment, the successful execution of service tasks heavily relies on the robot's capability to identify and understand objects within its surrounding. This crucial process predominantly takes place during task planning, prior to the actual performance of service tasks. Therefore, it
In the field of machine learning, multi-view clustering aims to reveal hidden clustering patterns across different data perspectives. However, traditional methods often struggle due to their reliance on low-order similarity data. To overcome this, we propose a new approach that integrates the learni…
In domestic environments, the conventional organization of objects by service robots often relies on the inherent properties of each object, such as placing fragile bowls in enclosed cupboards. However, this approach tends to overlook the importance of the orderly arrangement of objects, neglecting…
We present a new column generation approach based on Machine Learning (ML) for solving combinatorial optimization problems. The aim of our method is to generate high-quality columns that belong to an optimal integer solution, in contrast to the traditional approach that aims at solving linear progra…
Standing upon the intersection of traditional beamformers and deep neural networks, we propose a causal neural beamformer paradigm called Embedding and Beamforming, and two core modules are devised accordingly, namely EM and BM. For EM, instead of estimating spatial covariance matrix explicitly, the…
Column Generation (CG) is an effective method for solving large-scale optimization problems. CG starts by solving a subproblem with a subset of columns (i.e., variables) and gradually includes new columns that can improve the solution of the current subproblem. The new columns are generated as neede…
"Panoramic images have become increasingly popular as omnidirectional panoramic technology has advanced. Many datasets and works resort to object detection to better understand the content of the panoramic image. These datasets and detectors use a Bounding Field of View (BFoV) as a bounding box in p…
While the deep learning techniques promote the rapid development of the speech enhancement (SE) community, most schemes only pursue the performance in a black-box manner and lack adequate model interpretability. Inspired by Taylor's approximation theory, we propose an interpretable decoupling-style…
As one of the fundamental components of object detection, intersection-over-union (IoU) calculations between two bounding boxes play an important role in samples selection, NMS operation and evaluation of object detection algorithms. This procedure is well-defined and solved for planar images, while…
This paper describes a three-stage acoustic echo cancellation (AEC) and suppression framework for the ICASSP 2021 AEC Challenge. In the first stage, a partitioned block frequency domain adaptive filtering is implemented to cancel the linear echo components without introducing the near-end speech dis…
It remains a tough challenge to recover the speech signals contaminated by various noises under real acoustic environments. To this end, we propose a novel system for denoising in the complicated applications, which is mainly comprised of two pipelines, namely a two-stage network and a post-processi…