An overview of noise-robust automatic speech recognition
New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …
with mobile devices and home entertainment systems, increasingly require automatic …
Machine learning paradigms for speech recognition: An overview
L Deng, X Li - IEEE Transactions on Audio, Speech, and …, 2013 - ieeexplore.ieee.org
Automatic Speech Recognition (ASR) has historically been a driving force behind many
machine learning (ML) techniques, including the ubiquitously used hidden Markov model …
machine learning (ML) techniques, including the ubiquitously used hidden Markov model …
Librispeech: an asr corpus based on public domain audio books
This paper introduces a new corpus of read English speech, suitable for training and
evaluating speech recognition systems. The LibriSpeech corpus is derived from audiobooks …
evaluating speech recognition systems. The LibriSpeech corpus is derived from audiobooks …
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition
(LVSR) that leverages recent advances in using deep belief networks for phone recognition …
(LVSR) that leverages recent advances in using deep belief networks for phone recognition …
Parallel training of DNNs with natural gradient and parameter averaging
We describe the neural-network training framework used in the Kaldi speech recognition
toolkit, which is geared towards training DNNs with large amounts of training data using …
toolkit, which is geared towards training DNNs with large amounts of training data using …
Maximum likelihood linear transformations for HMM-based speech recognition
MJF Gales - Computer speech & language, 1998 - Elsevier
This paper examines the application of linear transformations for speaker and environmental
adaptation in an HMM-based speech recognition system. In particular, transformations that …
adaptation in an HMM-based speech recognition system. In particular, transformations that …
Improving deep neural network acoustic models using generalized maxout networks
Recently, maxout networks have brought significant improvements to various speech
recognition and computer vision tasks. In this paper we introduce two new types of …
recognition and computer vision tasks. In this paper we introduce two new types of …
End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition
In hidden Markov model (HMM) based automatic speech recognition (ASR) system,
modeling the statistical relationship between the acoustic speech signal and the HMM states …
modeling the statistical relationship between the acoustic speech signal and the HMM states …
Method and system for non-parametric voice conversion
I Agiomyrgiannakis - US Patent 9,183,830, 2015 - Google Patents
GIOL I5/04(2013.01) A method and system is disclosed for non-parametric speech GIOL
I5/4(2006.01) conversion. A text-to-speech (TTS) synthesis system may GIOL I3/02(2013.01) …
I5/4(2006.01) conversion. A text-to-speech (TTS) synthesis system may GIOL I3/02(2013.01) …
[图书][B] Speech synthesis and recognition
W Holmes - 2002 - taylorfrancis.com
With the growing impact of information technology on daily life, speech is becoming
increasingly important for providing a natural means of communication between humans …
increasingly important for providing a natural means of communication between humans …