相关论文: GNCformer Enhanced Self-attention for Automatic Sp…

Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…

Image restoration tasks traditionally rely on convolutional neural networks. However, given the local nature of the convolutional operator, they struggle to capture global information. The promise of attention mechanisms in Transformers is…

Session-based recommendation systems suggest relevant items to users by modeling user behavior and preferences using short-term anonymous sessions. Existing methods leverage Graph Neural Networks (GNNs) that propagate and aggregate…

Joint modeling of multi-speaker ASR and speaker diarization has recently shown promising results in speaker-attributed automatic speech recognition (SA-ASR).Although being able to obtain state-of-the-art (SOTA) performance, most of the…

With recent advances of diffusion model, generative speech enhancement (SE) has attracted a surge of research interest due to its great potential for unseen testing noises. However, existing efforts mainly focus on inherent properties of…

Transformer-based speech recognition models have achieved great success due to the self-attention (SA) mechanism that utilizes every frame in the feature extraction process. Especially, SA heads in lower layers capture various phonetic…

We present an Encoder-Decoder Attention Transformer, EDAFormer, which consists of the Embedding-Free Transformer (EFT) encoder and the all-attention decoder leveraging our Embedding-Free Attention (EFA) structure. The proposed EFA is a…

In this paper, we propose AUREXA-SE (Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement), a progressive bimodal framework tailored for audio-visual speech enhancement…

Beyond the Transformer, it is important to explore how to exploit the capacity of the MetaFormer, an architecture that is fundamental to the performance improvements of the Transformer. Previous studies have exploited it only for the…

Conventional Deep Learning frameworks for continuous sign language recognition (CSLR) are comprised of a single or multi-modal feature extractor, a sequence-learning module, and a decoder for outputting the glosses. The sequence learning…

Transformer has shown promising results in many sequence to sequence transformation tasks recently. It utilizes a number of feed-forward self-attention layers to replace the recurrent neural networks (RNN) in attention-based encoder decoder…

We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs.…

Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information. However, prior work on statistical machine translation has shown that extending the basic…

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

This paper introduces Meta-PerSER, a novel meta-learning framework that personalizes Speech Emotion Recognition (SER) by adapting to each listener's unique way of interpreting emotion. Conventional SER systems rely on aggregated…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Essay writing is a critical component of student assessment, yet manual scoring is labor-intensive and inconsistent. Automated Essay Scoring (AES) offers a promising alternative, but current approaches face limitations. Recent studies have…

For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is essential to improve its performance. Traditional attentive…

In human-computer interaction, Speech Emotion Recognition (SER) plays an essential role in understanding the user's intent and improving the interactive experience. While similar sentimental speeches own diverse speaker characteristics but…

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…