Related papers: E-Branchformer: Branchformer with Enhanced merging…
We propose a new end-to-end neural diarization (EEND) system that is based on Conformer, a recently proposed neural architecture that combines convolutional mappings and Transformer to model both local and global dependencies in speech. We…
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…
Online speech recognition, where the model only accesses context to the left, is an important and challenging use case for ASR systems. In this work, we investigate augmenting neural encoders for online ASR by incorporating structured…
Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…
Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…
Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model…
The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in…
On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…
To address the issue of poor generalization ability in end-to-end speech recognition models within deep learning, this study proposes a new Conformer-based speech recognition model called "Conformer-R" that incorporates the R-drop…
This paper presents an end-to-end model designed to improve automatic speech recognition (ASR) for a particular speaker in a crowded, noisy environment. The model utilizes a single-channel speech enhancement module that isolates the…
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can…
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…
Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…
We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our…
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…
The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare their accuracy and training times: (i) a recurrent model using LSTMs; (ii) a fully…
Due to the mismatch between the source and target domains, how to better utilize the biased word information to improve the performance of the automatic speech recognition model in the target domain becomes a hot research topic. Previous…
Conformers have recently been proposed as a promising modelling approach for automatic speech recognition (ASR), outperforming recurrent neural network-based approaches and transformers. Nevertheless, in general, the performance of these…
Recently, there has been an increasing interest in unifying streaming and non-streaming speech recognition models to reduce development, training and deployment cost. The best-known approaches rely on either window-based or dynamic…
Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid…