Related papers: Pay Attention to Hard Trials

Machine learning systems impact many stakeholders and groups of users, often disparately. Prior studies have reconciled conflicting user preferences by aggregating a high volume of manually labeled pairwise comparisons, but this technique…

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

In this report, we describe our submitted system for track 2 of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). We fuse a variety of good-performing models ranging from supervised models to self-supervised learning(SSL)…

Since perception tests are highly time-consuming, there is a need to automate as many operations as possible, such as stimulus generation, procedure control, perception testing, and data analysis. The computer-driven system we are…

In this technical report we describe the IDLAB top-scoring submissions for the VoxCeleb Speaker Recognition Challenge 2020 (VoxSRC-20) in the supervised and unsupervised speaker verification tracks. For the supervised verification tracks we…

This paper presents the SJTU system for both text-dependent and text-independent tasks in short-duration speaker verification (SdSV) challenge 2021. In this challenge, we explored different strong embedding extractors to extract robust…

Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments. Augmenting these systems with visual signals has the potential to improve robustness to noise. However, audio-visual…

In this paper, we address the problem of speaker verification in conditions unseen or unknown during development. A standard method for speaker verification consists of extracting speaker embeddings with a deep neural network and processing…

Speech recognition is very challenging in student learning environments that are characterized by significant cross-talk and background noise. To address this problem, we present a bilingual speech recognition system that uses an…

Audio-visual automatic speech recognition is a promising approach to robust ASR under noisy conditions. However, up until recently it had been traditionally studied in isolation assuming the video of a single speaking face matches the…

Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. In audio/speech signal processing, a wide range of…

Recent research in speaker verification has increasingly focused on achieving robust and reliable recognition under challenging channel conditions and noisy environments. Identifying speakers in radio communications is particularly…

Automating primary stress identification has been an active research field due to the role of stress in encoding meaning and aiding speech comprehension. Previous studies relied mainly on traditional acoustic features and English datasets.…

The performances of the automatic speaker verification (ASV) systems degrade due to the reduction in the amount of speech used for enrollment and verification. Combining multiple systems based on different features and classifiers…

Speaker identification, determining which character said each utterance in literary text, benefits many downstream tasks. Most existing approaches use expert-defined rules or rule-based features to directly approach this task, but these…

Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored. We study the transfer learning capabilities of such models on bioacoustic…

Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their…

Vision-language (VL) models, pretrained on colossal image-text datasets, have attained broad VL competence that is difficult to evaluate. A common belief is that a small number of VL skills underlie the variety of VL tests. In this paper,…

Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations obtained from…

We introduce a method to identify speakers by computing with high-dimensional random vectors. Its strengths are simplicity and speed. With only 1.02k active parameters and a 128-minute pass through the training data we achieve Top-1 and…