For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks,
...
This paper presents a speaking-rate-controllable HiFi-GAN neural vocoder...
The acoustic and linguistic features are important cues for the spoken
l...
In order to reduce domain discrepancy to improve the performance of
cros...
Generative probability models are widely used for speaker verification (...
Navigation guided by natural language instructions is particularly suita...
Placing objects is a fundamental task for domestic service robots (DSRs)...
The task for speaker verification (SV) is to decide an utterance is spok...
Due to the mismatch of statistical distributions of acoustic speech betw...
In this paper, we propose a quasi-periodic parallel WaveGAN (QPPWG) wave...
Domestic service robots (DSRs) are a promising solution to the shortage ...
In this paper, we propose a parallel WaveGAN (PWG)-like neural vocoder w...
Convolutional neural network (CNN) is an indispensable building block fo...
In this study, we focus on multimodal language understanding for fetchin...
In this paper, we address the automatic sentence generation of fetching
...
In this paper, we address multimodal language understanding for unconstr...
In a noisy environment, a lossy speech signal can be automatically resto...
This paper focuses on a multimodal language understanding method for
car...
The target task of this study is grounded language understanding for dom...
Speech enhancement model is used to map a noisy speech to a clean speech...
This study proposes a fully convolutional network (FCN) model for raw
wa...