Probabilistic time series forecasting is crucial in many application domains, such as retail, ecommerce, finance, and biology. With the increasing availability of large volumes data, a number neural architectures have been proposed for this problem. In particular, Transformer-based methods achieve state-of-the-art performance on real-world benchmarks. However, these require parameters to be lea...

The traditional vocoders have the advantages of high synthesis efficiency, strong interpretability, and speech editability, while neural advantage quality. To combine two vocoders, inspired by deterministic plus stochastic model, this paper proposes a novel vocoder named NeuralDPS which can retain quality acquire efficiency noise controllability. Firstly, framework contains four modules: source...

Electro-laryngeal (EL) speech has poor intelligibility and naturalness, which hampers the popular use of electro-larynx. Voice conversion (VC) can enhance EL speech. However, if to be enhanced is with complicated tone variation rules in Mandarin, enhancement will less effective. This because source (Mandarin speech) target (normal are not strictly parallel. We propose using cycle-consistent gen...

Ensuring the best quality and performance of modern speech technologies, today, is possible based on widespread use machine learning methods. The idea this project to study implement an end-to-end system automatic recognition using methods, as well develop new mathematical models algorithms for solving problem agglutinative (Turkic) languages. Many research papers have shown that deep methods m...

Energy disaggregation, a.k.a. Non-Intrusive Load Monitoring, aims to separate the energy consumption of individual appliances from readings a mains power meter measuring total of, e.g., whole house. can be useful in many applications, providing appliance-level feedback end users help them understand their and ultimately save energy. Recently, with availability large-scale datasets, various neur...

We present a scalable and efficient neural waveform coding system for speech compression. formulate the problem as an autoencoding task, where convolutional network (CNN) performs encoding decoding codec (NWC) during its feedforward routine. The proposed NWC also defines quantization entropy trainable module, so artifacts bitrate control are handled optimization process. achieve efficiency by i...

Tensor2Tensor is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer model. 1 Neural Machine Translation Background Machine translation using deep neural networks achieved great success with sequence-tosequence models (Sutskever et al., 2014; Bahdanau et al., 2014; Cho et al., 2014) t...

Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database. However, speech synthesis and voice conversion paradigms that are not considered in the ASVspoof2015 database are appearing. Such examples include...

The combination of wavelet theory and neural networks has lead to the development of wavelet networks. Wavelet networks are feed-forward neural networks using wavelets as activation function. Wavelet networks have been used in classification and identification problems with some success. The strength of wavelet networks lies in their capabilities of catching essential features in „frequency-ric...