This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-
TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit …

Concerns regarding the vulnerability of automatic speaker verification (ASV) technology
against spoofing can undermine confidence in its reliability and form a barrier to exploitation …

Identifying the gender of a person and his age by way of speaking is considered a crucial
task in computer vision. It is a very important and active research topic with many areas of …

In conventional speaker recognition methods based on Mel-frequency cepstral coefficients
(MFCCs), phase information has hitherto been ignored. In this paper, we propose a phase …

In this paper, we develop two corpora for speech synthesis research. Thanks to
improvements in machine learning techniques, including deep learning, speech synthesis is …

Constructing deep neural network (DNN) acoustic models from limited training data is an
important issue for the development of automatic speech recognition (ASR) applications that …

Denoising autoencoder is applied to reverberant speech recognition as a noise robust front-
end to reconstruct clean speech spectrum from noisy input. In order to capture context effects …

This paper proposes a novel countermeasure framework to detect spoofing attacks to
reduce the vulnerability of automatic speaker verification (ASV) systems. Recently, ASV …

Although speech derived from read texts, news broadcasts, and other similar prepared
contexts can be recognized with high accuracy, recognition performance drastically …

This paper addresses end-to-end speech recognition which directly maps acoustic features
to a word sequence. The acoustic-to-word model is attractive since it does not require an …