Related papers: Range-Based Equal Error Rate for Spoof Localizatio…

Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…

Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake detection a much-needed area of research. While researchers have presented various techniques for detecting audio spoofs, it is often unclear exactly…

Speaker diarization systems segment a conversation recording based on the speakers' identity. Such systems can misclassify the speaker of a portion of audio due to a variety of factors, such as speech pattern variation, background noise,…

Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed…

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Voice conversion (VC) aims at conversion of speaker characteristic without altering content. Due to training data limitations and modeling imperfections, it is difficult to achieve believable speaker mimicry without introducing processing…

We consider the multiple breakpoint detection problem, which is concerned with detecting the locations of several distinct changes in a one-dimensional noisy data series. We propose the breakpointError, a function that can be used to…

When the task of locating manipulation regions in partially-fake audio (PFA) involves cross-domain datasets, the performance of deep learning models drops significantly due to the shift between the source and target domains. To address this…

Region-based methods have proven necessary for improving segmentation accuracy of neuronal structures in electron microscopy (EM) images. Most region-based segmentation methods use a scoring function to determine region merging. Such…

Recent advances in speech foundation models are largely driven by scaling both model size and data, enabling them to perform a wide range of tasks, including speech recognition. Traditionally, ASR models are evaluated using metrics like…

Code-switching, the alternation of languages within a single discourse, presents a significant challenge for Automatic Speech Recognition. Despite the unique nature of the task, performance is commonly measured with established metrics such…

This paper introduces NoRefER, a novel referenceless quality metric for automatic speech recognition (ASR) systems. Traditional reference-based metrics for evaluating ASR systems require costly ground-truth transcripts. NoRefER overcomes…

Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical workaround, it often introduces systematic, accent-specific…

Sound event detection (SED) and localization refer to recognizing sound events and estimating their spatial and temporal locations. Using neural networks has become the prevailing method for SED. In the area of sound localization, which is…

The randomized-feature approach has been successfully employed in large-scale kernel approximation and supervised learning. The distribution from which the random features are drawn impacts the number of features required to efficiently…

Signal-to-noise ratio (SNR) statistics play a central role in many applications. A common situation where SNR is studied is when a continuous time signal is sampled at a fixed frequency with some noise in the background. While estimation…

Many endeavors have sought to develop countermeasure techniques as enhancements on Automatic Speaker Verification (ASV) systems, in order to make them more robust against spoof attacks. As evidenced by the latest ASVspoof 2019…

Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the…

Precise subtraction of foreground sources is crucial for detecting and estimating 21cm HI signals from the Epoch of Reionization (EoR). We quantify how imperfect point source subtraction due to limitations of the measurement dataset yields…