33 accepted papers
Advanced sound zone control (SZC) techniques typically rely on massive multi-channel loudspeaker arrays to create high-contrast personal sound zones, making single-loudspeaker SZC seem impossible. In this Letter, we challenge this paradigm by introducing the multi-carrier parametric loudspeaker (MCP…
Generative models have shown remarkable performance in speech enhancement (SE), achieving superior perceptual quality over traditional discriminative approaches. However, existing generative SE approaches often overlook the risk of hallucination under severe noise, leading to incorrect spoken conten
Sparse query-based detectors have emerged as the dominant paradigm in camera-only 3D object detection, owing to their exceptional performance and computational efficiency. A central component of these approaches is the use of reference points, which serve as learnable spatial anchors to guide queri
Flow matching and diffusion bridge models have emerged as leading paradigms in generative speech enhancement, modeling stochastic processes between paired noisy and clean speech signals based on principles such as flow matching, score matching, and Schrödinger bridge. In this paper, we present a fra
While previous diffusion-based neural vocoders typically follow a noise-to-data generation pipe-line, the linear-degradation prior of the mel-spectrogram is often neglected, resulting in limited generation quality. By revisiting the vocoding task and excavating its connection with the signal restora
Whisper to Normal voice conversion (W2N) holds great promise for assistive communication and healthcare, making it an exciting area of research and development. Recent advancements in W2N are predominantly driven by self-supervised speech representation learning (SSL) techniques. While effective, SS…
Human understanding of text depends on general semantic concepts of words rather than their superficial forms. To what extent does our human intuition transfer to language models? In this work, we study the degree to which current multilingual language models (mLMs) understand based on subword-level…
Sentiment analysis is rapidly advancing by utilizing various data modalities (e.g., text, video, and audio). However, most existing techniques only learn the atomic-level features that reflect strong correlations, while ignoring more complex compositions in multimodal data. Moreover, they also negle…
The partitioned block frequency domain Kalman Filter (PBFDKF) has been applied in acoustic feedback cancellation (AFC) due to its fast convergence and low steady-state misalignment. However, in cases where the feedback path experiences abrupt changes, the Kalman filter, once it reaches a steady stat…
Although deep learning (DL) based end-to-end models have shown outstanding performance in multi-channel speech extraction, their practical applications on edge devices are restricted due to their high computational complexity. In this paper, we propose a hybrid system that can more effectively integ…
Effective group recommendation systems play a pivotal role in enriching the information consumption of users from different groups. Existing group recommendation approaches face challenges such as the sparsity of the rating matrix and low specificity between user clusters, leading to cold-start issu…
While modern deep learning-based models have significantly outperformed traditional methods in the area of speech enhancement, they often necessitate a lot of parameters and extensive computational power, making them impractical to be deployed on edge devices in real-world applications. In this pape…
Existing passage retrieval systems typically adopt a two-stage retrieve-then-rerank pipeline. To obtain an effective reranking model, many prior works have focused on improving the model architectures, such as leveraging powerful pretrained large language models (LLM) and designing better objective…
One of the important tasks of auditory attention decoding is to identify the attended speaker’s direction from the listener’s EEG signals. Compared to rule-based methods, deep neural networks (DNNs) have recently shown significantly better identification accuracy, especially with short decision wind…
This paper summarizes a hybrid multi-channel speech enhancement system for the ICASSP Signal Processing Grand Challenge: Clarity Challenge (Speech Enhancement for Hearing Aids) 2023. The system consists of a rule-based dereverberation module, a multi-channel enhancement module, and a post-processing…
Few-Shot Class-Incremental Learning (FSCIL) aims to continually learn novel classes based on only few training samples, which poses a more challenging task than the well-studied Class-Incremental Learning (CIL) due to data scarcity. While knowledge distillation, a prevailing technique in CIL, can al…
Recent developments of the application of Contrastive Learning in Semi-Supervised Learning (SSL) have demonstrated significant advancements, as a result of its exceptional ability to learn class-aware cluster representations and the full exploitation of massive unlabeled data. However, mismatched in…
Domain adaptation aims to transfer the knowledge learned on (data-rich) source domains to (low-resource) target domains, and a popular method is invariant representation learning, which matches and aligns the data distributions on the feature space. Although this method is studied extensively and ap…
Recently, Visual Question Answering(VQA), which is required to generate the answer by understanding both visual and textual content, has attracted considerable research interest. Most existing works extract visual features with the CNN network and learn its feature embedding with an attention mechan…
Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech. Previous works introduce the speaker embedding into speech enhancement models by means of concatenation or affine transformation. In this paper, we propose a speaker attentive…
Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other retrieval tasks where supervision is limited, with the implicit assumption that it is possible to generalize from one task to all the rest. However, t…
Perceptual evaluation of speech quality (PESQ) is widely accepted as an effective objective metric closely related to the speech quality sensed by human listening perception. Due to its evaluation complexity and non-differentiability, PESQ is difficult to include in the cost function for deep learni…
"Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the teacher model, i.e., the local knowledge. However, the empirical…
State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms, however, are not without flaws, i.e., running the model on…
It has been shown that dual encoders trained on one domain often fail to generalize to other domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual encoder, where the final score is simply a dot-product between a query vector and a passage vector, is too limited co…
Open Set Recognition (OSR) has been an emerging topic. Besides recognizing predefined classes, the system needs to reject the unknowns. Prototype learning is a potential manner to handle the problem, as its ability to improve intra-class compactness of representations is much needed in discriminatio…
We propose a neural event coreference model in which event coreference is jointly trained with five tasks: trigger detection, entity coreference, anaphoricity determination, realis detection, and argument extraction. To guide the learning of this complex model, we incorporate cross-task consistency…
Despite recent promising results on the application of span-based models for event reference interpretation, there is a lack of understanding of what has been improved. We present an empirical analysis of a state-of-the-art span-based event reference systems with the goal of providing the general NL…
In the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion. We systematically investigate how these techniques contribute to the performance of the retrieval system and how they complement each other. We propose a multi-s…
Motivated by the recent successful application of span-based models to entity-based information extraction tasks, we investigate span-based models for event coreference resolution, focusing on determining (1) whether the successes of span-based models of entity coreference can be extended to event c…
Online secondary path modeling is appealing for most active noise control systems due to its benefit of effective tracking of the varying acoustic environment and possible variation of the control sources and sensors. However, the usually utilized additive noise method inevitably leads to the increa…
Click-through rate (CTR) prediction is one of the fundamental tasks for e-commerce search engines. As search becomes more personalized, it is necessary to capture the user interest from rich behavior data. Existing user behavior modeling algorithms develop different attention mechanisms to emphasize…
Deep image embedding aims at learning a convolutional neural network (CNN) based mapping function that maps an image to a feature vector. The embedding quality is usually evaluated by the performance in image search tasks. Since very few users bother to open the second page search results, top-k pre…