相关论文: Squeezeformer: An Efficient Transformer for Automa…

Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural network's exploiting of local features. In Conformer, two…

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,…

Transformers have enabled impressive improvements in deep learning. They often outperform recurrent and convolutional models in many tasks while taking advantage of parallel processing. Recently, we proposed the SepFormer, which obtains…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher…

Recently Convolution-augmented Transformer (Conformer) has shown promising results in Automatic Speech Recognition (ASR), outperforming the previous best published Transformer Transducer. In this work, we believe that the output information…

The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using…

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Automatic speech recognition (ASR) systems developed in recent years have shown promising results with self-attention models (e.g., Transformer and Conformer), which are replacing conventional recurrent neural networks. Meanwhile, a…

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…

Over 70 million people worldwide experience stuttering, yet most automatic speech systems misinterpret disfluent utterances or fail to transcribe them accurately. Existing methods for stutter correction rely on handcrafted feature…

Recently, Conformer as a backbone network for end-to-end automatic speech recognition achieved state-of-the-art performance. The Conformer block leverages a self-attention mechanism to capture global information, along with a convolutional…

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords as basic units in developing such systems. However, 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…

This paper presents a novel memory-efficient model compression approach for Conformer ASR and speech foundation systems. Our approach features a unique "small-to-large" design. A compact "seed" model containing a few Conformer or…

Neural end-to-end text-to-speech (TTS) , which adopts either a recurrent model, e.g. Tacotron, or an attention one, e.g. Transformer, to characterize a speech utterance, has achieved significant improvement of speech synthesis. However, it…

Recently, conformer-based end-to-end automatic speech recognition, which outperforms recurrent neural network based ones, has received much attention. Although the parallel computing of conformer is more efficient than recurrent neural…

End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train…