相关论文: Adapter-Based Multi-Agent AVSR Extension for Pre-T…

Recently, Transformers have been introduced into the field of acoustics recognition. They are pre-trained on large-scale datasets using methods such as supervised learning and semi-supervised learning, demonstrating robust generality--It…

Audiovisual segmentation (AVS) aims to identify visual regions corresponding to sound sources, playing a vital role in video understanding, surveillance, and human-computer interaction. Traditional AVS methods depend on large-scale…

Current state-of-the-art speech recognition models are trained to map acoustic signals into sub-lexical units. While these models demonstrate superior performance, they remain vulnerable to out-of-distribution conditions such as background…

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

Recent advances in reasoning models have shown remarkable progress in text-based domains, but transferring those capabilities to multimodal settings, e.g., to allow reasoning over audio-visual data, still remains a challenge, in part…

Human speech processing is inherently multimodal, where visual cues (lip movements) help to better understand the speech in noise. Lip-reading driven speech enhancement significantly outperforms benchmark audio-only approaches at low…

The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and…

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…

Single-word Automatic Speech Recognition (ASR) is a challenging task due to the lack of linguistic context and sensitivity to noise, pronunciation variation, and channel artifacts, especially in low-resource, communication-critical domains…

Lip Reading, or Visual Automatic Speech Recognition (V-ASR), is a complex task requiring the interpretation of spoken language exclusively from visual cues, primarily lip movements and facial expressions. This task is especially challenging…

OpenAI's Whisper Automated Speech Recognition model excels in generalizing across diverse datasets and domains. However, this broad adaptability can lead to diminished performance in tasks requiring recognition of specific vocabularies.…

State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can only finetune lightweight neural network layers on top of…

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Audio-Visual Speech Recognition (AVSR) seeks to model, and thereby exploit, the dynamic relationship between a human voice and the corresponding mouth movements. A recently proposed multimodal fusion strategy, AV Align, based on…

Audiovisual instance segmentation (AVIS) requires accurately localizing and tracking sounding objects throughout video sequences. Existing methods suffer from visual bias stemming from two fundamental issues: uniform additive fusion…

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…

Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off…

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…