Related papers: Improving Non-native Word-level Pronunciation Scor…

Own voice pickup for hearables in noisy environments benefits from using both an outer and an in-ear microphone outside and inside the occluded ear. Due to environmental noise recorded at both microphones, and amplification of the own voice…

The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models. In this paper, we mainly focus on designing an efficient data-centric scheme to improve robustness…

While improvements have been made in automatic speech recognition performance over the last several years, machines continue to have significantly lower performance on accented speech than humans. In addition, the most significant…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

The classification of acoustic environments allows for machines to better understand the auditory world around them. The use of deep learning in order to teach machines to discriminate between different rooms is a new area of research.…

The system we used for Task 6 (Automated Audio Captioning)of the Detection and Classification of Acoustic Scenes and Events(DCASE) 2020 Challenge combines three elements, namely, dataaugmentation, multi-task learning, and post-processing,…

Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations and benchmarks has impeded recent progress, resulting in…

We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the…

As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in…

This study discusses the effect of semi-supervised learning in combination with pretrained language models for data-to-text generation. It is not known whether semi-supervised learning is still helpful when a large-scale language model is…

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…

This paper introduces RawBoost, a data boosting and augmentation method for the design of more reliable spoofing detection solutions which operate directly upon raw waveform inputs. While RawBoost requires no additional data sources, e.g.…

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and…

Recent work has demonstrated that using parameter efficient tuning techniques such as prefix tuning (or P-tuning) on pretrained language models can yield performance that is comparable or superior to fine-tuning while dramatically reducing…

Training NLP systems typically assumes access to annotated data that has a single human label per example. Given imperfect labeling from annotators and inherent ambiguity of language, we hypothesize that single label is not sufficient to…

In this paper, we present a customizable datacentric system that automatically generates common misspellings for complex health-related terms. The spelling variant generator relies on a dense vector model learned from large unlabeled text,…

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…

In this progress paper the previous results of the single note recognition by deep learning are presented. The several ways for data augmentation and "artificial semantic" augmentation are proposed to enhance efficiency of deep learning…

This study investigates the impact of integrating a dataset of disordered speech recordings ($\sim$1,000 hours) into the fine-tuning of a near state-of-the-art ASR baseline system. Contrary to what one might expect, despite the data being…