相关论文: Transformer-based end-to-end speech recognition wi…

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…

Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer…

Aspect-based sentiment analysis (ABSA) and Targeted ASBA (TABSA) allow finer-grained inferences about sentiment to be drawn from the same text, depending on context. For example, a given text can have different targets (e.g., neighborhoods)…

Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and…

Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani…

The Transformer architecture has been well adopted as a dominant architecture in most sequence transduction tasks including automatic speech recognition (ASR), since its attention mechanism excels in capturing long-range dependencies. While…

Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…

We propose Low-Rank Sparse Attention (Lorsa), a sparse replacement model of Transformer attention layers to disentangle original Multi Head Self Attention (MHSA) into individually comprehensible components. Lorsa is designed to address the…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used…

Many real-world applications involve multivariate, geo-tagged time series data: at each location, multiple sensors record corresponding measurements. For example, air quality monitoring system records PM2.5, CO, etc. The resulting…

Recently, Transformers have shown promising performance in various vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute, especially for the high-resolution vision tasks. Local…

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the…

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to…

Self-attention relies on positional embeddings to encode input order. Relative Position (RelPos) embeddings are widely used in Automatic Speech Recognition (ASR). However, RelPos has quadratic time complexity to input length and is often…

Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence in such models, in this paper we introduce the concept of…

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input. To remedy this issue, we propose a self-attention layer…

Attention calculation is extremely time-consuming for long-sequence inference tasks, such as text or image/video generation, in large models. To accelerate this process, we developed a low-precision, mathematically-equivalent algorithm…

Self-attention (SA) network has shown profound value in image captioning. In this paper, we improve SA from two aspects to promote the performance of image captioning. First, we propose Normalized Self-Attention (NSA), a reparameterization…