Sequence-to-sequence models have been widely used in end-to-end speech processing,
for example, automatic speech recognition (ASR), speech translation (ST), and text-to …

An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the
largest corpus which is suitable for conducting the speech recognition research and building …

Data augmentation is a common strategy adopted to increase the quantity of training data,
avoid overfitting and improve robustness of the models. In this paper, we investigate audio …

Sensing technologies place significant interest in the use of biometrics for the recognition
and assessment of individuals. Pattern mining techniques have established a critical step in …

We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We
learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) …

The mainstream neural text-to-speech (TTS) pipeline is a cascade system, including an
acoustic model (AM) that predicts acoustic feature from the input transcript and a vocoder …

Communication has been an important aspect of human life, civilization, and globalization
for thousands of years. Biometric analysis, education, security, healthcare, and smart cities …

End-to-end automatic speech recognition (ASR) can significantly reduce the burden of
developing ASR systems for new languages, by eliminating the need for linguistic …

The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens,
has been proven superior to traditional acoustic feature mel-spectrograms in terms of …

In this paper, a novel two-branch neural network model structure is proposed for multimodal
emotion recognition, which consists of a time synchronous branch (TSB) and a time …