Related papers: Sim-T: Simplify the Transformer Network by Multipl…
End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…
Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…
Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time…
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…
Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…
We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM…
Recent deep learning models have achieved high performance in speech enhancement; however, it is still challenging to obtain a fast and low-complexity model without significant performance degradation. Previous knowledge distillation…
In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…
Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resource-constrained…
We propose a novel transfer learning method for speech emotion recognition allowing us to obtain promising results when only few training data is available. With as low as 125 examples per emotion class, we were able to reach a higher…
Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…
Large-scale transformer models have shown remarkable performance in language modelling tasks. However, such models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To…
Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…
Transformer-based models have achieved remarkable success, but their core components, Transformer layers, are largely heuristics-driven and engineered from the bottom up, calling for a prototypical model with high interpretability and…
Online multichannel speech enhancement has been intensively studied recently. Though Mel-scale frequency is more matched with human auditory perception and computationally efficient than linear frequency, few works are implemented in a…
Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…
In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on…
Speech classification tasks often require powerful language understanding models to grasp useful features, which becomes problematic when limited training data is available. To attain superior classification performance, we propose to…
The effective incorporation of cross-utterance information has the potential to improve language models (LMs) for automatic speech recognition (ASR). To extract more powerful and robust cross-utterance representations for the Transformer LM…
End-to-end multi-talker speech recognition has garnered great interest as an effective approach to directly transcribe overlapped speech from multiple speakers. Current methods typically adopt either 1) single-input multiple-output (SIMO)…