相关论文: Conformers are All You Need for Visual Speech Reco…

Current vision language pretraining models are dominated by methods using region visual features extracted from object detectors. Given their good performance, the extract-then-process pipeline significantly restricts the inference speed…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Self-supervised learning has emerged as a key approach for learning generic representations from speech data. Despite promising results in downstream tasks such as speech recognition, speaker verification, and emotion recognition, a…

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigned Conformer with a…

Automatic lip-reading (ALR) aims to automatically transcribe spoken content from a speaker's silent lip motion captured in video. Current mainstream lip-reading approaches only use a single visual encoder to model input videos of a single…

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…

The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques…

Realistic, high-fidelity 3D facial animations are crucial for expressive avatar systems in human-computer interaction and accessibility. Although prior methods show promising quality, their reliance on the mesh domain limits their ability…

Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…

Visual speech recognition is a technique to identify spoken content in silent speech videos, which has raised significant attention in recent years. Advancements in data-driven deep learning methods have significantly improved both the…

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain…

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…

Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typically multi-headed, where each head has an independent set…

This work presents a scalable solution to open-vocabulary visual speech recognition. To achieve this, we constructed the largest existing visual speech recognition dataset, consisting of pairs of text and video clips of faces speaking…

Visual speech recognition (VSR), which decodes spoken words from video data, offers significant benefits, particularly when audio is unavailable. However, the high dimensionality of video data leads to prohibitive computational costs that…

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…