Deep neural networks (DNNs) have gained remarkable success in speech recognition,
partially attributed to the flexibility of DNN models in learning complex patterns of speech …

Our previous work, the unified source-filter GAN (uSFGAN) vocoder, introduced a novel
architecture based on the source-filter theory into the parallel waveform generative …

We explore options to use Transformer networks in neural transducer for end-to-end speech
recognition. Transformer networks use self-attention for sequence modeling and comes with …

Enhancing coded speech suffering from far-end acoustic background noise, quantization
noise, and potentially transmission errors is a challenging task. In this paper, we propose …

This paper introduces a novel neural audio codec targeting high waveform sampling rates
and low bitrates named APCodec, which seamlessly integrates the strengths of parametric …

State-of-the-art speech recognition systems typically employ neural network acoustic
models. However, compared to Gaussian mixture models, deep neural network (DNN) …

This paper describes the extension and optimisation of our previous work on very deep
convolutional neural networks (CNNs) for effective recognition of noisy speech in the Aurora …

Deep neural networks (DNN) have gained remarkable success in speech recognition,
partially attributed to its flexibility in learning complex patterns of speech signals. This …

The performance of automatic speech recognition (ASR) has improved tremendously due to
the application of deep neural networks (DNNs). Despite this progress, building a new ASR …

Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-
end speech recognition. However, the recurrent structure makes it difficult for parallelization …