Related papers: Enhancing the Unified Streaming and Non-streaming …

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

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…

We develop a predictive-first optimisation framework for streaming hidden Markov models. Unlike classical approaches that prioritise full posterior recovery under a fully specified generative model, we assume access to regime-specific…

A study is presented in which a contrastive learning approach is used to extract low-dimensional representations of the acoustic environment from single-channel, reverberant speech signals. Convolution of room impulse responses (RIRs) with…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…

Recommender systems trained on user interaction data are susceptible to behavioral intensity imbalance--a systematic distortion arising from heterogeneous engagement patterns across users. This imbalance skews feedback signals such that…

While internet-scale data often comes in pairs (e.g., audio/image, image/text), we often want to perform inferences over modalities unseen together in the training data (e.g., audio/text). Empirically, this can often be addressed by…

Considering the abundance of unlabeled speech data and the high labeling costs, unsupervised learning methods can be essential for better system development. One of the most successful methods is contrastive self-supervised methods, which…

Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…

As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important…

Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee on the downstream…

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

Contrastive learning-based recommendation algorithms have significantly advanced the field of self-supervised recommendation, particularly with BPR as a representative ranking prediction task that dominates implicit collaborative filtering.…

Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused…

Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of representations…

We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a…

After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy. Contrastive learning has demonstrated its great potential in learning from unlabeled data. However,…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…