Search

In recent years, there has been an increasing focus on user convenience, leading to increased interest in text-based keyword enrollment systems for keyword spotting (KWS). Since the system utilizes text input during the enrollment phase and audio input during actual usage, we call this task audio-text based KWS. To enable this task, both acoustic and text encoders are typically trained using deep metric learning loss functions, such as triplet- and proxy-based losses. This study aims to improve existing methods by leveraging the structural relations within acoustic embeddings and within text embeddings. Unlike previous studies that only compare acoustic and text embeddings on a point-to-point basis, our approach focuses on the relational structures within the embedding space by introducing the concept of Relational Proxy Loss (RPL). By incorporating RPL, we demonstrated improved performance on the Wall Street Journal (WSJ) corpus., Comment: 5 pages, 2 figures, Accepted by Interspeech 2024

Recently, many mesh-based graph neural network (GNN) models have been proposed for modeling complex high-dimensional physical systems. Remarkable achievements have been made in significantly reducing the solving time compared to traditional numerical solvers. These methods are typically designed to i) reduce the computational cost in solving physical dynamics and/or ii) propose techniques to enhance the solution accuracy in fluid and rigid body dynamics. However, it remains under-explored whether they are effective in addressing the challenges of flexible body dynamics, where instantaneous collisions occur within a very short timeframe. In this paper, we present Hierarchical Contact Mesh Transformer (HCMT), which uses hierarchical mesh structures and can learn long-range dependencies (occurred by collisions) among spatially distant positions of a body -- two close positions in a higher-level mesh correspond to two distant positions in a lower-level mesh. HCMT enables long-range interactions, and the hierarchical mesh structure quickly propagates collision effects to faraway positions. To this end, it consists of a contact mesh Transformer and a hierarchical mesh Transformer (CMT and HMT, respectively). Lastly, we propose a flexible body dynamics dataset, consisting of trajectories that reflect experimental settings frequently used in the display industry for product designs. We also compare the performance of several baselines using well-known benchmark datasets. Our results show that HCMT provides significant performance improvements over existing methods. Our code is available at https://github.com/yuyudeep/hcmt., Comment: Accepted at ICLR 2024

Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training effectiveness of SA-EEND models, we propose the use of auxiliary losses for the SA heads of the transformer layers. Specifically, we assume that the attention weight matrices of an SA layer are redundant if their patterns are similar to those of the identity matrix. We then explicitly constrain such matrices to exhibit specific speaker activity patterns relevant to voice activity detection or overlapped speech detection tasks. Consequently, we expect the proposed auxiliary losses to guide the transformer layers to exhibit more diverse patterns in the attention weights, thereby reducing the assumed redundancies in the SA heads. The effectiveness of the proposed method is demonstrated using the simulated and CALLHOME datasets for two-speaker diarization tasks, reducing the diarization error rate of the conventional SA-EEND model by 32.58% and 17.11%, respectively., Comment: 5 pages, ICASSP2023 (Accepted)

With increasing interest in applying machine learning to develop healthcare solutions, there is a desire to create interpretable deep learning models for survival analysis. In this paper, we extend the Neural Additive Model (NAM) by incorporating pairwise feature interaction networks and equip these models with loss functions that fit both proportional and non-proportional extensions of the Cox model. We show that within this extended framework, we can construct non-proportional hazard models, which we call TimeNAM, that significantly improve performance over the standard NAM model architecture on benchmark survival datasets. We apply these model architectures to data from the Electronic Health Record (EHR) database of Seoul National University Hospital Gangnam Center (SNUHGC) to build an interpretable neural network survival model for gastric cancer prediction. We demonstrate that on both benchmark survival analysis datasets, as well as on our gastric cancer dataset, our model architectures yield performance that matches, or surpasses, the current state-of-the-art black-box methods., Comment: Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 14 pages

Developing a single-microphone speech denoising or dereverberation front-end for robust automatic speaker verification (ASV) in noisy far-field speaking scenarios is challenging. To address this problem, we present a novel front-end design that involves a recently proposed extension of the weighted prediction error (WPE) speech dereverberation algorithm, the virtual acoustic channel expansion (VACE)-WPE. It is demonstrated experimentally in this study that unlike the conventional WPE algorithm, the VACE-WPE can be explicitly trained to cancel out both late reverberation and background noise. To build the front-end, the VACE-WPE is first independently (pre)trained to produce "noisy" dereverberated signals. Subsequently, given a pretrained speaker embedding model, the VACE-WPE is additionally fine-tuned within a task-specific optimization (TSO) framework, causing the speaker embedding extracted from the processed signal to be similar to that extracted from the "noise-free" target signal. Moreover, to extend the application of the proposed front-end to more general, unconstrained "in-the-wild" ASV scenarios beyond controlled far-field conditions, we propose a distortion regularization method for the VACE-WPE within the TSO framework. The effectiveness of the proposed approach is verified on both far-field and in-the-wild ASV benchmarks, demonstrating its superiority over fully neural front-ends and other TSO methods in various cases.

Koolen et al. showed that if a graph with smallest eigenvalue at least $-3$ has large minimal valency, then it is $2$-integrable. In this paper, we will focus on the sesqui-regular graphs with smallest eigenvalue at least $-3$ and study their integrability.

Speech dereverberation is an important issue for many real-world speech processing applications. Among the techniques developed, the weighted prediction error (WPE) algorithm has been widely adopted and advanced over the last decade, which blindly cancels out the late reverberation component from the reverberant mixture of microphone signals. In this study, we extend the neural-network-based virtual acoustic channel expansion (VACE) framework for the WPE-based speech dereverberation, a variant of the WPE that we recently proposed to enable the use of dual-channel WPE algorithm in a single-microphone speech dereverberation scenario. Based on the previous study, some ablation studies are conducted regarding the constituents of the VACE-WPE in an offline processing scenario. These studies help understand the dynamics of the system, thereby simplifying the architecture and leading to the introduction of new strategies for training the neural network for the VACE. Experimental results in noisy reverberant environments reveal that VACE-WPE considerably outperforms its single-channel counterpart in terms of objective speech quality and is complementary to the single-channel WPE when employed as the front-end for the far-field automatic speech recognizer., Comment: 13 pages, 12 figures, 10 tables

In this note, we study the maximum number $N_\alpha(d)$ of a system of equiangular lines in $\mathbb{R}^d$ with cosine $\alpha$, where $\frac{1}{\alpha}$ is not an odd positive integer. This note is motivated by a remark in a $2018$ paper by Balla, Dr\"{a}xler, Keevash and Sudakov., Comment: 4 pages

Let $\lambda\geq2$ be an integer. For strongly regular graphs with parameters $(v, k, a,c)$ and smallest eigenvalue $-\lambda$, Neumaier gave two bounds on $c$ by using algebraic property of strongly regular graphs. In this paper, we will study a new class of regular graphs called sesqui-regular graphs, which contains strongly regular graphs as a subclass, and prove that for a sesqui-regular graph with parameters $(v,k,c)$ and smallest eigenvalue at least $-\lambda$, if $k$ is very large, then either $c \leq \lambda^2(\lambda -1)$ or $v-k-1 \leq \frac{(\lambda-1)^2}{4} + 1$ holds.