Related papers: Tiny-Sepformer: A Tiny Time-Domain Transformer Net…

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional…

Transformer encoder-decoder models have achieved great performance in dialogue generation tasks, however, their inability to process long dialogue history often leads to truncation of the context To address this problem, we propose a novel…

Speaker verification (SV) aims to determine whether the speaker's identity of a test utterance is the same as the reference speech. In the past few years, extracting speaker embeddings using deep neural networks for SV systems has gone…

Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head…

Attention-based encoder-decoder, e.g. transformer and its variants, generates the output sequence in an autoregressive (AR) manner. Despite its superior performance, AR model is computationally inefficient as its generation requires as many…

Recently, Convolutional Neural Network (CNN) and Long short-term memory (LSTM) based models have been introduced to deep learning-based target speaker separation. In this paper, we propose an Attention-based neural network (Atss-Net) in 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…

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection.…

Speech separation algorithms are often used to separate the target speech from other interfering sources. However, purely neural network based speech separation systems often cause nonlinear distortion that is harmful for automatic speech…

Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a key issue to…

Efficient transformer variants with linear time complexity have been developed to mitigate the quadratic computational overhead of the vanilla transformer. Among them are low-rank projection methods such as Linformer and kernel-based…

Punctuation and word casing prediction are necessary for automatic speech recognition (ASR). With the popularity of on-device end-to-end streaming ASR systems, the on-device punctuation and word casing prediction become a necessity while we…

Speech separation, the task of isolating multiple speech sources from a mixed audio signal, remains challenging in noisy environments. In this paper, we propose a generative correction method to enhance the output of a discriminative…

Brain tissue segmentation has demonstrated great utility in quantifying MRI data through Voxel-Based Morphometry and highlighting subtle structural changes associated with various conditions within the brain. However, manual segmentation is…

In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has…

Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and…

We present an upper bound for the Single Channel Speech Separation task, which is based on an assumption regarding the nature of short segments of speech. Using the bound, we are able to show that while the recent methods have made…

Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an efficient neural network…

To extract the voice of a target speaker when mixed with a variety of other sounds, such as white and ambient noises or the voices of interfering speakers, we extend the Transformer network to attend the most relevant information with…

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. To solve this problem, this paper proposes a…