Unsupervised training and directed manual transcription for LVCSR
A significant cost in obtaining acoustic training data is the generation of accurate
transcriptions. When no transcription is available, unsupervised training techniques must be …
transcriptions. When no transcription is available, unsupervised training techniques must be …
Improving interpretability and regularization in deep learning
Deep learning approaches yield state-of-the-art performance in a range of tasks, including
automatic speech recognition. However, the highly distributed representation in a deep …
automatic speech recognition. However, the highly distributed representation in a deep …
Minimising biasing word errors for contextual ASR with the tree-constrained pointer generator
Contextual knowledge is essential for reducing speech recognition errors on high-valued
long-tail words. This paper proposes a novel tree-constrained pointer generator (TCPGen) …
long-tail words. This paper proposes a novel tree-constrained pointer generator (TCPGen) …
An information-extraction approach to speech processing: Analysis, detection, verification, and recognition
CH Lee, SM Siniscalchi - Proceedings of the IEEE, 2013 - ieeexplore.ieee.org
The field of automatic speech recognition (ASR) has enjoyed more than 30 years of
technology advances due to the extensive utilization of the hidden Markov model (HMM) …
technology advances due to the extensive utilization of the hidden Markov model (HMM) …
HMMs and related speech recognition technologies
S Young - Springer handbook of speech processing, 2008 - Springer
Almost all present-day continuous speech recognition (CSR) systems are based on hidden
Markov models (HMMs). Although the fundamentals of HMM-based CSR have been …
Markov models (HMMs). Although the fundamentals of HMM-based CSR have been …
[PDF][PDF] Semi-supervised maximum mutual information training of deep neural network acoustic models.
Abstract Maximum Mutual Information (MMI) is a popular discriminative criterion that has
been used in supervised training of acoustic models for automatic speech recognition …
been used in supervised training of acoustic models for automatic speech recognition …
Improving rare word recognition with lm-aware mwer training
Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E)
models on words rarely seen during training, when used in either the shallow fusion or the …
models on words rarely seen during training, when used in either the shallow fusion or the …
[DOC][DOC] Deep learning for signal and information processing
This short monograph contains the material expanded from two tutorials that the authors
gave, one at APSIPA in October 2011 and the other at ICASSP in March 2012. Substantial …
gave, one at APSIPA in October 2011 and the other at ICASSP in March 2012. Substantial …
Prosodic feature-based discriminatively trained low resource speech recognition system
Speech recognition has been an active field of research in the last few decades since it
facilitates better human–computer interaction. Native language automatic speech …
facilitates better human–computer interaction. Native language automatic speech …
Analysis of MLP-based hierarchical phoneme posterior probability estimator
J Pinto, S Garimella, M Magimai-Doss… - … on Audio, Speech …, 2010 - ieeexplore.ieee.org
We analyze a simple hierarchical architecture consisting of two multilayer perceptron (MLP)
classifiers in tandem to estimate the phonetic class conditional probabilities. In this …
classifiers in tandem to estimate the phonetic class conditional probabilities. In this …