Related papers: Improving Audio Event Recognition with Consistency…

Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly…

Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition (ASR) systems. Generally, training data for EC are collected by automatically pairing a large set of…

State-of-the-art automatic speech recognition (ASR) systems struggle with the lack of data for rare accents. For sufficiently large datasets, neural engines tend to outshine statistical models in most natural language processing problems.…

Sound event detection (SED) is the task of identifying sound events along with their onset and offset times. A recent, convolutional neural networks based SED method, proposed the usage of depthwise separable (DWS) and time-dilated…

Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and…

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…

Lack of large, well-annotated emotional speech corpora continues to limit the performance and robustness of speech emotion recognition (SER), particularly as models grow more complex and the demand for multimodal systems increases. While…

Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under…

In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples, Selective Output…

This paper investigates the feasibility of class-incremental learning (CIL) for Sound Event Localization and Detection (SELD) tasks. The method features an incremental learner that can learn new sound classes independently while preserving…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We present ARCH, a comprehensive benchmark for evaluating ARL methods…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability. We investigate supervised contrastive learning (SupCon) as a lightweight,…

The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance…

Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs - as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the…

Automatic speech recognition systems are part of people's daily lives, embedded in personal assistants and mobile phones, helping as a facilitator for human-machine interaction while allowing access to information in a practically intuitive…

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…