Related papers: Noise in Relation Classification Dataset TACRED: C…
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…
In high-dimensional data, structured noise caused by observed and unobserved factors affecting multiple target variables simultaneously, imposes a serious challenge for modeling, by masking the often weak signal. Therefore, (1) explaining…
Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…
Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision, making post-hoc dataset revision a practical problem. Existing noisy-label and data-cleaning methods largely operate at the…
Distantly supervised models are very popular for relation extraction since we can obtain a large amount of training data using the distant supervision method without human annotation. In distant supervision, a sentence is considered as a…
Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level,…
Most current speech enhancement (SE) methods recover clean speech from noisy inputs by directly estimating time-frequency masks or spectrums. However, these approaches often neglect the distinct attributes, such as semantic content and…
Large datasets in NLP suffer from noisy labels, due to erroneous automatic and human annotation procedures. We study the problem of text classification with label noise, and aim to capture this noise through an auxiliary noise model over…
Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world…
Although automatic pathological speech detection approaches show promising results when clean recordings are available, they are vulnerable to additive noise. Recently it has been shown that databases commonly used to develop and evaluate…
We propose a novel objective evaluation metric for synthesized audio in text-to-audio (TTA), aiming to improve the performance of TTA models. In TTA, subjective evaluation of the synthesized sound is an important, but its implementation…
Text-based person search aims to retrieve the specified person images given a textual description. The key to tackling such a challenging task is to learn powerful multi-modal representations. Towards this, we propose a Relation and…
Training deep neural networks (DNNs) with noisy labels is a challenging problem due to over-parameterization. DNNs tend to essentially fit on clean samples at a higher rate in the initial stages, and later fit on the noisy samples at a…
Recent advancements in Automatic Piano Transcription (APT) have significantly improved system performance, but the impact of noisy environments on the system performance remains largely unexplored. This study investigates the impact of…
A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are…
Relation Extraction (RE) is a pivotal task in automatically extracting structured information from unstructured text. In this paper, we present a multi-faceted approach that integrates representative examples and through co-set expansion.…
Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these…
Distant supervision based methods for entity and relation extraction have received increasing popularity due to the fact that these methods require light human annotation efforts. In this paper, we consider the problem of \textit{shifted…
The quality of the speech communication systems, which include noise suppression algorithms, are typically evaluated in laboratory experiments according to the ITU-T Rec. P.835, in which participants rate background noise, speech signal,…
Composed Image Retrieval (CIR) is a challenging image retrieval paradigm that enables to retrieve target images based on multimodal queries consisting of reference images and modification texts. Although substantial progress has been made…