Multi-basis adaptive neural network for rapid adaptation in speech recognition
Recent progress in acoustic modeling with deep neural network has significantly improved
the performance of automatic speech recognition systems. However, it remains as an open …
the performance of automatic speech recognition systems. However, it remains as an open …
[PDF][PDF] An improved DNN-based approach to mispronunciation detection and diagnosis of L2 learners' speech.
We extend the Goodness of Pronunciation (GOP) algorithm from the conventional GMM-
HMM to DNN-HMM and further optimize the GOP measure toward L2 language learners' …
HMM to DNN-HMM and further optimize the GOP measure toward L2 language learners' …
Two efficient lattice rescoring methods using recurrent neural network language models
An important part of the language modelling problem for automatic speech recognition
(ASR) systems, and many other related applications, is to appropriately model long-distance …
(ASR) systems, and many other related applications, is to appropriately model long-distance …
[图书][B] Computers in the human interaction loop
It is a common experience in our modern world, for us humans to be overwhelmed by the
complexities of technological artifacts around us, and by the attention they demand. While …
complexities of technological artifacts around us, and by the attention they demand. While …
Spectro-temporal deep features for disordered speech assessment and recognition
Automatic recognition of disordered speech remains a highly challenging task to date.
Sources of variability commonly found in normal speech including accent, age or gender …
Sources of variability commonly found in normal speech including accent, age or gender …
Multiple proposals for continuous arabic sign language recognition
The deaf community relies on sign language as the primary means of communication. For
the millions of people around the world who suffer from hearing loss, interaction with hearing …
the millions of people around the world who suffer from hearing loss, interaction with hearing …
Improving broadcast news transcription by lightly supervised discriminative training
HY Chan, P Woodland - 2004 IEEE International Conference …, 2004 - ieeexplore.ieee.org
We present our experiments on lightly supervised discriminative training with large amounts
of broadcast news data for which only closed caption transcriptions are available (TDT data) …
of broadcast news data for which only closed caption transcriptions are available (TDT data) …
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 …
[PDF][PDF] Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages.
This paper presents the progress of acoustic models for lowresourced languages
(Assamese, Bengali, Haitian Creole, Lao, Zulu) developed within the second evaluation …
(Assamese, Bengali, Haitian Creole, Lao, Zulu) developed within the second evaluation …
GFCC based discriminatively trained noise robust continuous ASR system for Hindi language
A statistically designed Automatic Speech Recognition (ASR) system extracts features from
speech signals using feature extraction methods, links the extracted features with the …
speech signals using feature extraction methods, links the extracted features with the …