Related papers: Enhancing the Unified Streaming and Non-streaming …
Contrastive learning has recently established itself as a powerful self-supervised learning framework for extracting rich and versatile data representations. Broadly speaking, contrastive learning relies on a data augmentation scheme to…
In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning. In particular, self-supervised learning (SSL) of utterance-level speech representation can be used in speech…
This paper addresses the challenge of developing a robust audio-visual deepfake detection model. In practical use cases, new generation algorithms are continually emerging, and these algorithms are not encountered during the development of…
Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…
We propose a streaming non-autoregressive (non-AR) decoding algorithm to deliberate the hypothesis alignment of a streaming RNN-T model. Our algorithm facilitates a simple greedy decoding procedure, and at the same time is capable of…
There is growing interest in unifying the streaming and full-context automatic speech recognition (ASR) networks into a single end-to-end ASR model to simplify the model training and deployment for both use cases. While in real-world ASR…
This paper studies a training method to jointly estimate an energy-based model and a flow-based model, in which the two models are iteratively updated based on a shared adversarial value function. This joint training method has the…
Graphs model complex relationships between entities, with nodes and edges capturing intricate connections. Node representation learning involves transforming nodes into low-dimensional embeddings. These embeddings are typically used as…
Environmental Sound Classification (ESC) is a challenging field of research in non-speech audio processing. Most of current research in ESC focuses on designing deep models with special architectures tailored for specific audio datasets,…
We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for…
Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the…
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…
Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…
Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…
Self-supervised learning (SSL) has drawn an increased attention in the field of speech processing. Recent studies have demonstrated that contrastive learning is able to learn discriminative speaker embeddings in a self-supervised manner.…
The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. It is…
While representation learning and generative modeling seek to understand visual data, unifying both domains remains unexplored. Recent Unified Self-Supervised Learning (SSL) methods have started to bridge the gap between both paradigms.…
A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…
Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing…
Deep Learning approaches have brought solutions, with impressive performance, to general classification problems where wealthy of annotated data are provided for training. In contrast, less progress has been made in continual learning of a…