Sorry, you need to enable JavaScript to visit this website.

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the effectiveness and robustness of automatic speech recognition (ASR) contextual biasing without introducing additional parameters. A common challenge in previous literature is that the word error rate (WER) reduction brought by contextual biasing diminishes as the number of bias phrases increases. To address this challenge, we employ a GA loss as an additional training objective besides the Transducer loss.

Deep learning-based speech enhancement methods have shown promising result in recent years. However, in practical applications, the model size and computational complexity are important factors that limit their use in end-products. Therefore, in products that require real-time speech enhancement with limited resources, such as TWS headsets, hearing aids, IoT devices, etc., ultra-lightweight models are necessary. In this paper, an ultra-lightweight network FSPEN is proposed for real-time speech enhancement task.

This paper focuses on the transition of automatic speaker verification systems from time delay neural networks (TDNN) to ResNet-based networks. TDNN-based systems use a statistics pooling layer to aggregate temporal information which is suitable for two-dimensional tensors. Even though ResNet-based models produce three-dimensional tensors, they continue to incorporate the statistics pooling layer.

Since the goals of both Moment Retrieval (MR) and Highlight Detection (HD) are to quickly obtain the required content from the video according to user needs, several works have attempted to take advantage of the commonality between both tasks to design transformer-based networks for joint MR and HD. Although these methods achieve impressive performance, they still face some problems: \textbf{a)} Semantic gaps across different modalities. \textbf{b)} Various durations of different query-relevant moments and highlights. \textbf{c)} Smooth transitions among diverse events.

Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), especially at finer granularity, e.g., phoneme level. This paper aims at alleviating the peaky behavior for CTC and improve its suitability for forced alignment generation, by leveraging label priors, so that the scores of alignment paths containing fewer blanks are boosted and maximized during training.

Heterogeneity is present in Alzheimer’s disease (AD), making it challenging to study. To address this, we propose a graph neural network (GNN) approach to identify disease subtypes from magnetic resonance imaging (MRI) and functional MRI (fMRI) scans. Subtypes are identified by encoding the patients’ scans in brain graphs (via cortical similarity networks) and clustering the representations learnt by the GNN.

Detecting microexpressions presents formidable challenges, primarily due to their fleeting nature and the limited diversity in existing datasets. Our studies find that these datasets exhibit a pronounced bias towards specific ethnicities and suffer from significant imbalances in terms of both class and gender representation among the samples. These disparities create fertile ground for various biases to permeate deep learning models, leading to skewed results and inadequate portrayal of specific demographic groups.

Deep learning-based methods provide remarkable performance in a number of computational imaging problems. Examples include end-to-end trained networks that map measurements to unknown signals, plug-and-play (PnP) methods that use pretrained denoisers as image prior, and model-based unrolled networks that train artifact removal blocks. Many of these methods lack robustness and fail to generalize with distribution shifts in data, measurements, and noise. In this paper, we present a simple framework to perform domain adaptation as data and measurement distribution shifts.

The prominence of a spoken word is the degree to which an average native listener perceives the word as salient or emphasized relative to its context. Speech prominence estimation is the process of assigning a numeric value to the prominence of each word in an utterance. These prominence labels are useful for linguistic analysis, as well as training automated systems to perform emphasis-controlled text-to-speech or emotion recognition. Manually annotating prominence is time-consuming and expensive, which motivates the development of automated methods for speech prominence estimation.

The prominence of a spoken word is the degree to which an average native listener perceives the word as salient or emphasized relative to its context. Speech prominence estimation is the process of assigning a numeric value to the prominence of each word in an utterance. These prominence labels are useful for linguistic analysis, as well as training automated systems to perform emphasis-controlled text-to-speech or emotion recognition. Manually annotating prominence is time-consuming and expensive, which motivates the development of automated methods for speech prominence estimation.