Related papers: Investigation of Deep Neural Network Acoustic Mode…

Despite the recent advancements in Automatic Speech Recognition (ASR), the recognition of accented speech still remains a dominant problem. In order to create more inclusive ASR systems, research has shown that the integration of accent…

Recently, multi-channel speech enhancement has drawn much interest due to the use of spatial information to distinguish target speech from interfering signal. To make full use of spatial information and neural network based masking…

Two new approaches to accent classification and conversion are presented and explored, respectively. The first topic is Chinese accent classification/recognition. The second topic is the use of encoder-decoder models for end-to-end Chinese…

For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks, compared to character-based modeling units, pronunciation-based modeling units could improve the sharing of modeling units in model training but meet homophone…

Highway deep neural network (HDNN) is a type of depth-gated feedforward neural network, which has shown to be easier to train with more hidden layers and also generalise better compared to conventional plain deep neural networks (DNNs).…

Deep Neural Networks (DNNs) have already become a crucial computational approach to revealing the spatial patterns in the human brain; however, there are three major shortcomings in utilizing DNNs to detect the spatial patterns in…

Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and…

This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing…

While neural networks for learning representation of multi-view data have been previously proposed as one of the state-of-the-art multi-view dimension reduction techniques, how to make the representation discriminative with only a small…

The direct expansion of deep neural network (DNN) based wide-band speech enhancement (SE) to full-band processing faces the challenge of low frequency resolution in low frequency range, which would highly likely lead to deteriorated…

Batch normalization (BN) is an effective method to accelerate model training and improve the generalization performance of neural networks. In this paper, we propose an improved batch normalization technique called attentive batch…

The performance of speaker diarization is strongly affected by its clustering algorithm at the test stage. However, it is known that clustering algorithms are sensitive to random noises and small variations, particularly when the clustering…

Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…

Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pre-training on a…

This paper proposes a speech emotion recognition method based on speech features and speech transcriptions (text). Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCC) help retain emotion-related low-level…

Recurrent neural networks (RNNs) have shown significant improvements in recent years for speech enhancement. However, the model complexity and inference time cost of RNNs are much higher than deep feed-forward neural networks (DNNs).…

This paper outlines the methodology for modeling tonal learning in fully unsupervised models of human language acquisition. Tonal patterns are among the computationally most complex learning objectives in language. We argue that a realistic…

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models. ASR…

The development of multi-modal large language models (LLMs) leads to intelligent approaches capable of speech interactions. As one of the most widely spoken languages globally, Mandarin is supported by most models to enhance their…

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the…