Reducing errors by increasing the error rate: MLP Acoustic Modeling for Broadcast News Transcription
Published 1 January 1999Open access
Nelson Morgan, Daniel P. W. Ellis, Eric Fosler‐Lussier, Adam Janin, Brian Kingsbury
Citations8
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Some aspects of a Broadcast News recognition system based on hybrid HMM/MLP acoustic modeling are described, including the use of novel ‘modulation spectrogram’ features which are combined with conventional models at the posterior probability level, and an investigation of the interaction of model size and training set size for an multilayer perceptron (MLP) acoustic classifier.
Abstract
We describe some aspects of a Broadcast News recognition system based on hybrid HMM/MLP acoustic modeling. These include the use of novel 'modulation spectrogram' features which are combined with conventional models at the posterior probability level, some experiments with nonlinear segment normalization, and an investigation of the interaction of model size and training set size for an multilayer perceptron (MLP) acoustic classifier. We also report preliminary results of incorporating gender-dependence into this system.
Keywords
Computer Science
The Journal of the Acoustical Society of AmericaPerceptual linear predictive (PLP) analysis of speech
2,539 Citations1990Hynek Heřmanský
A new technique for the analysis of speech, the perceptual linear predictive (PLP) technique, which uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum, and yields a low-dimensional representation of speech.
Computer Speech & LanguageMaximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
2,210 Citations1995C.J. Leggetter, Philip C. Woodland
An important feature of the method is that arbitrary adaptation data can be used—no special enrolment sentences are needed and that as more data is used the adaptation performance improves.
IEEE Transactions on Speech and Audio ProcessingRASTA processing of speech
1,816 Citations1994Hynek Heřmanský, N. Morgan
The theoretical and experimental foundations of the RASTA method are reviewed, the relationship with human auditory perception is discussed, the original method is extended to combinations of additive noise and convolutional noise, and an application is shown to speech enhancement.
Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system
180 Citations1995João P. Neto, Luı́s B. Almeida +5 more
These techniques are applied to a well trained, speaker-independent, hybrid HMM-ANN system and the recognizer parameters are adapted to a new speaker through o -line procedures and show that speaker-adaptation within the hybrid framework can substantially improve system performance.
Speech CommunicationTowards increasing speech recognition error rates
147 Citations1996Hervé Bourlard, Hynek Heřmanský +1 more
Issues that will be addressed in this paper include: discrimination between rival utterance models, the role of prior information in speech recognition, merging the language and acoustic models, feature extraction and temporal information, and decoding procedures reflecting human perceptual properties.
ComputerSpert-II: a vector microprocessor system
100 Citations1996John Wawrzynek, Krste Asanović +4 more
A prototype full custom vector microprocessor, TO, is packaged as the Spert-II (Synthetic Perceptron Testbed II) workstation accelerator system, to accelerate multiparameter neural network training for speech recognition research.
Perceptually inspired signal processing strategies for robust speech recognition in reverberant environments
51 Citations1998Brian Kingsbury, Nelson Morgan
This work presentsceptually Inspired Signal-processing Strategies for Robust Speech Recognition in Reverberant Environments, a novel approach to signal-processing that automates the very labor-intensive and therefore time-heavy and expensive process of recognizing speech.
The 1997 HTK broadcast news transcription system
37 Citations1998PC Woodland, Thomas Hain +4 more
The recent development of the HTK broadcast news transcription system is presented, using data for which no manual preclassification or segmentation is available and therefore automatic techniques are required and compatible acoustic modelling strategies must be adopted.
Performance improvements through combining phone- and syllable-scale information in automatic speech recognition
28 Citations1998Su-Lin Wu, Brian Kingsbury +2 more
Phone and syllable-based systems are combined at three distinct levels of the recognition process — the frame, the syllable and the entire utterance, yielding a significant improvement in accuracy on a small-vocabulary, naturally spoken, telephone speech corpus.
Improved hidden Markov modeling for speaker-independent continuous speech recognition
26 Citations1990Xuedong Huang, Fil Alleva +4 more
Recent efforts to further improve the performance of the Sphinx system for speaker-independent continuous speech recognition are reported, with incorporation of additional dynamic features, semi-continuous hidden Markov models, and speaker clustering.
Columbia Academic Commons (Columbia University)An Overview of the SPRACH System for the Transcription of Broadcast News
25 Citations1999Gary Cook, James Christie +8 more
This paper describes the SPRACH system, a system based on the connectionist-HMM framework and uses both recurrent neural network and multi-layer perceptron acoustic models, and describes recent developments to CHRONOS, a time-first stack decoder.