Voice, as input, has progressively become popular on mobiles and seems t...
Reducing noise interference is crucial for automatic speech recognition ...
Automatic Pronunciation Assessment (APA) plays a vital role in
Computer-...
As an indispensable ingredient of computer-assisted pronunciation traini...
We present a novel algorithm for learning the parameters of hidden Marko...
Conversational speech normally is embodied with loose syntactic structur...
End-to-end (E2E) neural modeling has emerged as one predominant school o...
Recently, end-to-end (E2E) models, which allow to take spectral vector
s...
With the acceleration of globalization, more and more people are willing...
In recent decades, many studies have suggested that phase information is...
Due to the unprecedented breakthroughs brought about by deep learning, s...
An important research direction in automatic speech recognition (ASR) ha...
More recently, Bidirectional Encoder Representations from Transformers (...
Mispronunciation detection and diagnosis (MDD) is designed to identify
p...
In this report, we describe our submission to the VoxCeleb Speaker
Recog...
Frequently asked question (FAQ) retrieval, with the purpose of providing...
Tremendous amounts of multimedia associated with speech information are
...
Mispronunciation detection and diagnosis (MDD) is a core component of
co...
Recently, end-to-end (E2E) automatic speech recognition (ASR) systems ha...
This paper describes the NTNU ASR system participating in the Interspeec...
Contextualized representation models such as ELMo (Peters et al., 2018a)...
Work on the problem of contextualized word representation -- the develop...
In the context of natural language processing, representation learning h...
Word embedding methods revolve around learning continuous distributed ve...
Extractive summarization aims at selecting a set of indicative sentences...
Owing to the rapidly growing multimedia content available on the Interne...