In this work, we present a novel method, named AV2vec, for learning
audi...
Lip region-of-interest (ROI) is conventionally used for visual input in ...
We present the Tongue and Lips corpus (TaL), a multi-speaker corpus of a...
With the development of automatic speech recognition (ASR) and text-to-s...
This paper presents an adversarial learning method for recognition-synth...
Automatic speaker verification (ASV) is one of the most natural and
conv...
In this paper, a method for non-parallel sequence-to-sequence (seq2seq) ...
This paper presents methods of making using of text supervision to impro...
In this paper, a neural network named Sequence-to- sequence ConvErsion
N...
This paper proposes a forward attention method for the sequenceto- seque...