Uncertainty estimation in deep learning with application to spoken language assessment
A Malinin - 2019 - repository.cam.ac.uk
Since convolutional neural networks (CNNs) achieved top performance on the ImageNet
task in 2012, deep learning has become the preferred approach to addressing computer …
task in 2012, deep learning has become the preferred approach to addressing computer …
Context-aware goodness of pronunciation for computer-assisted pronunciation training
Mispronunciation detection is an essential component of the Computer-Assisted
Pronunciation Training (CAPT) systems. State-of-the-art mispronunciation detection models …
Pronunciation Training (CAPT) systems. State-of-the-art mispronunciation detection models …
End-to-end neural network based automated speech scoring
L Chen, J Tao, S Ghaffarzadegan… - 2018 IEEE international …, 2018 - ieeexplore.ieee.org
In recent years, machine learning models for automated speech scoring systems were
mainly built using data-driven approaches with handcrafted features as one of the main …
mainly built using data-driven approaches with handcrafted features as one of the main …
Automated Scoring of Nonnative Speech Using the SpeechRaterSM v. 5.0 Engine
This research report provides an overview of the R&D efforts at Educational Testing Service
related to its capability for automated scoring of nonnative spontaneous speech with the …
related to its capability for automated scoring of nonnative spontaneous speech with the …
[HTML][HTML] A situational analysis of current speech-synthesis systems for child voices: A scoping review of qualitative and quantitative evidence
(1) Background: Speech synthesis has customarily focused on adult speech, but with the
rapid development of speech-synthesis technology, it is now possible to create child voices …
rapid development of speech-synthesis technology, it is now possible to create child voices …
Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition
R Serizel, D Giuliani - 2014 IEEE Spoken Language …, 2014 - ieeexplore.ieee.org
This paper introduces approaches based on vocal tract length normalisation (VTLN)
techniques for hybrid deep neural network (DNN)-hidden Markov model (HMM) automatic …
techniques for hybrid deep neural network (DNN)-hidden Markov model (HMM) automatic …
Deep-neural network approaches for speech recognition with heterogeneous groups of speakers including children
R Serizel, D Giuliani - Natural Language Engineering, 2017 - cambridge.org
This paper introduces deep neural network (DNN)–hidden Markov model (HMM)-based
methods to tackle speech recognition in heterogeneous groups of speakers including …
methods to tackle speech recognition in heterogeneous groups of speakers including …
[PDF][PDF] Pitch-Adaptive Front-End Features for Robust Children's ASR.
In the presented work, we explore some of the challenges in recognizing children's speech
on automatic speech recognition (ASR) systems developed using adults' speech. In such …
on automatic speech recognition (ASR) systems developed using adults' speech. In such …
Towards automatic assessment of spontaneous spoken English
With increasing global demand for learning English as a second language, there has been
considerable interest in methods of automatic assessment of spoken language proficiency …
considerable interest in methods of automatic assessment of spoken language proficiency …
Assessment of pitch-adaptive front-end signal processing for children's speech recognition
R Sinha, S Shahnawazuddin - Computer Speech & Language, 2018 - Elsevier
On account of large acoustic mismatch, automatic speech recognition (ASR) systems trained
using adults' speech data yield poor recognition performance when evaluated on children's …
using adults' speech data yield poor recognition performance when evaluated on children's …