An artificial neural network is an important model for training features of voice conversion (VC) tasks. Typically, neural networks (NNs) are very effective in processing nonlinear features, such as Mel Cepstral Coefficients (MCC), which represent the spectrum features. However, a simple representation of fundamental frequency (F0) is not enough for NNs to deal with emotional voice VC. This is because the time sequence of F0 for an emotional voice changes drastically. Therefore, in our previous method, we used the continuous wavelet transform (CWT) to decompose F0 into 30 discrete scales, each separated by one third of an octave, which can be trained by NNs for prosody modeling in emotional VC. In this study, we propose the arbitrary scales CWT (AS-CWT) method to systematically capture F0 features of different temporal scales, which can represent different prosodic levels ranging from micro-prosody to sentence levels. Meanwhile, the proposed method uses deep belief networks (DBNs) to pre-train the NNs that then convert spectral features. By utilizing these approaches, the proposed method can change the spectrum and the F0 for an emotional voice simultaneously as well as outperform other state-of-the-art methods in terms of emotional VC.

Text-to-Speech (TTS) aims to convert the input text to a human-like voice. With the development of deep learning, encoder-decoder based TTS models perform superior performance, in terms of naturalness, in mainstream languages such as Chinese, English, etc. Note that the linguistic information learning capability of the text encoder is the key. However, for TTS of low-resource agglutinative languages, the scale of the $< $ text, speech $>$ paired data is limited. Therefore, how to extract rich linguistic information from small-scale text data to enhance the naturalness of the synthesized speech, is an urgent issue that needs to be addressed. In this paper, we first collect a large unsupervised text data for BERT-like language model pre-training, and then adopt the trained language model to extract deep linguistic information for the input text of the TTS model to improve the naturalness of the final synthesized speech. It should be emphasized that in order to fully exploit the prosody-related linguistic information in agglutinative languages, we incorporated morphological information into the language model training and constructed a morphology-aware masking based BERT model (MAM-BERT). Experimental results based on various advanced TTS models validate the effectiveness of our approach. Further comparison of the various data scales also validates the effectiveness of our approach in low-resource scenarios.

Emotional voice conversion (VC) aims to convert a neutral voice to an emotional one while retaining the linguistic information and speaker identity. We note that the decoupling of emotional features from other speech information (such as content, speaker identity, etc.) is the key to achieving promising performance. Some recent attempts of speech representation decoupling on the neutral speech cannot work well on the emotional speech, due to the more complex entanglement of acoustic properties in the latter. To address this problem, here we propose a novel Source-Filter-based Emotional VC model (SFEVC) to achieve proper filtering of speaker-independent emotion cues from both the timbre and pitch features. Our SFEVC model consists of multi-channel encoders, emotion separate encoders, pre-trained speaker-dependent encoders, and the corresponding decoder. Note that all encoder modules adopt a designed information bottleneck auto-encoder. Additionally, to further improve the conversion quality for various emotions, a novel training strategy based on the 2D Valence-Arousal (VA) space is proposed. Experimental results show that the proposed SFEVC along with a VA training strategy outperforms all baselines and achieves the state-of-the-art performance in speaker-independent emotional VC with nonparallel data.

This paper proposes a novel approach, based on convolutional neural network (CNN) models, that forecasts the short-term crude oil futures prices with good performance. In our study, we confirm that artificial intelligence (AI)-based deep-learning approaches can provide more accurate forecasts of short-term oil prices than those of the benchmark Naive Forecast (NF) model. We also provide strong evidence that CNN models with matrix inputs are better at short-term prediction than neural network (NN) models with single-vector input, which indicates that strengthening the dependence of inputs and providing more useful information can improve short-term forecasting performance.

The choice of image feature representation plays a crucial role in the analysis of visual information. Although vast numbers of alternative robust feature representation models have been proposed to improve the performance of different visual tasks, most existing feature representations (e.g. handcrafted features or Convolutional Neural Networks (CNN)) have a relatively limited capacity to capture the highly orientation-invariant (rotation/reversal) features. The net consequence is suboptimal visual performance. To address these problems, this study adopts a novel transformational approach, which investigates the potential of using polar feature representations. Our low level consists of a histogram of oriented gradient, which is then binned using annular spatial bin-type cells applied to the polar gradient. This gives gradient binning invariance for feature extraction. In this way, the descriptors have significantly enhanced orientation-invariant capabilities. The proposed feature representation, termed it orientation-invariant histograms of oriented gradients (Oi-HOG), is capable of accurately processing facial expression recognition (FER). In the context of the CNN architecture, we propose two polar convolution operations, referred to as Full Polar Convolution (FPolarConv) and Local Polar Convolution (LPolarConv), and use these to develop polar architectures for the CNN orientation-invariant representation. Experimental results show that the proposed orientation-invariant image representation, based on polar models for both handcrafted features and deep learning features, is both competitive with state-of-the-art methods and maintains a compact representation on a set of challenging benchmark image datasets.