Speech style transfer

TL;DR: The proposed model, FastVC, is based on a conditional AutoEncoder trained on non-parallel data and requires no annotations at all, and outperforms the VC Challenge 2020 baselines on the cross-lingual task in terms of naturalness.

TL;DR: A speech analyzer includes a speech acquiring section, a frequency converting section, an autocorrelation section, and a pitch detection section as mentioned in this paper, where the pitch detection system determines the pitch frequency from the distance between two local crests or troughs of the waveform.

TL;DR: In this article, a voice identification method using a long short term memory model recurrent neural network (LSTM) was proposed. But the model was not designed for speech recognition.

TL;DR: In this article, a method and a system for detecting voice spoofing attack of speakers on the basis of deep learning is presented, which includes constructing audio-frequency training sets, initializing deep feed-forward neural networks and deep recurrent neural networks by the aid of multi-frame feature vectors and single-frame vector sequences of the training sets; respectively leading frame level and sequence level feature vectors of to-be-tested audio frequencies into two trained linear differential analysis models in test phases, weighting two obtained result grades to obtain scores and comparing the scores to predefined threshold values so

TL;DR: In this article, a phonotactic post-processor is configured to rescore the N-best phoneme candidates output by a primary ensemble phoneme neural network using a priori phono-temporal information.