Related papers: Contrastive Predictive Coding Based Feature for Au…
Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…
High-quality phrase representations are essential to finding topics and related terms in documents (a.k.a. topic mining). Existing phrase representation learning methods either simply combine unigram representations in a context-free manner…
End-to-end deep neural networks have achieved remarkable success across various domains but are often criticized for their lack of interpretability. While post hoc explanation methods attempt to address this issue, they often fail to…
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…
Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…
Code search aims to retrieve the code snippet that highly matches the given query described in natural language. Recently, many code pre-training approaches have demonstrated impressive performance on code search. However, existing code…
Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous ones as claimed that…
Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader…
Predictive Coding (PC) is a biologically-inspired learning framework characterised by local, parallelisable operations, properties that enable energy-efficient implementation on neuromorphic hardware. Despite this, extending PC effectively…
Video-grounded dialogue systems aim to integrate video understanding and dialogue understanding to generate responses that are relevant to both the dialogue and video context. Most existing approaches employ deep learning models and have…
Convolutional Sparse Coding (CSC) is an increasingly popular model in the signal and image processing communities, tackling some of the limitations of traditional patch-based sparse representations. Although several works have addressed the…
Contrastive approaches to representation learning have recently shown great promise. In contrast to generative approaches, these contrastive models learn a deterministic encoder with no notion of uncertainty or confidence. In this paper, we…
In this paper, an improved strategy for automated text dependent speaker identification system has been proposed in noisy environment. The identification process incorporates the Neuro- Genetic hybrid algorithm with cepstral based features.…
Dysarthric speech reconstruction is challenging due to its pathological sound patterns. Preserving speaker identity, especially without access to normal speech, is a key challenge. Our proposed approach uses contrastive learning to extract…
Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…
Audio anti-spoofing for automatic speaker verification aims to safeguard users' identities from spoofing attacks. Although state-of-the-art spoofing countermeasure(CM) models perform well on specific datasets, they lack generalization when…
In this paper, we introduce Continuation Passing C (CPC), a programming language for concurrent systems in which native and cooperative threads are unified and presented to the programmer as a single abstraction. The CPC compiler uses a…
Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…
Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables. Fair contrastive learning constructs negative pairs, for example,…
Teaching proofs is a crucial component of any undergraduate-level program that covers formal reasoning. We have developed a calculational reasoning format and refined it over several years of teaching a freshman-level course, "Logic and…