Results 1 
7 of
7
Connectionist speech recognition of Broadcast News
, 2002
"... This paper describes connectionist techniques for recognition of Broadcast News. The fundamental difference between connectionist systems and more conventional mixtureofGaussian systems is that connectionist models directly estimate posterior probabilities as opposed to likelihoods. Access to post ..."
Abstract

Cited by 31 (11 self)
 Add to MetaCart
This paper describes connectionist techniques for recognition of Broadcast News. The fundamental difference between connectionist systems and more conventional mixtureofGaussian systems is that connectionist models directly estimate posterior probabilities as opposed to likelihoods. Access to posterior probabilities has enabled us to develop a number of novel approaches to confidence estimation, pronunciation modelling and search. In addition we have investigated a new feature extraction technique based on the modulationfiltered spectrogram (MSG), and methods for combining multiple information sources. We have incorporated all of these techniques into a system for the transcription
Startsynchronous search for large vocabulary continuous speech recognition
 IEEE Trans. Speech and Audio Processing
"... Abstract — In this paper, we present a novel, efficient search strategy for large vocabulary continuous speech recognition. The search algorithm, based on a stack decoder framework, utilizes phonelevel posterior probability estimates (produced by a connectionist/hidden Markov model acoustic model) ..."
Abstract

Cited by 20 (10 self)
 Add to MetaCart
Abstract — In this paper, we present a novel, efficient search strategy for large vocabulary continuous speech recognition. The search algorithm, based on a stack decoder framework, utilizes phonelevel posterior probability estimates (produced by a connectionist/hidden Markov model acoustic model) as a basis for phone deactivation pruning—a highly efficient method of reducing the required computation. The singlepass algorithm is naturally factored into the timeasynchronous processing of the word sequence and the timesynchronous processing of the hidden Markov model state sequence. This enables the search to be decoupled from the language model while still maintaining the computational benefits of timesynchronous processing. The incorporation of the language model in the search is discussed and computationally cheap approximations to the full language model are introduced. Experiments were performed on the North American Business News task using a 60 000 word vocabulary and a trigram language model. Results indicate that the computational cost of the search may be reduced by more than a factor of 40 with a relative search error of less than 2 % using the techniques discussed in the paper. Index Terms — Hidden Markov model, large vocabulary continuous speech recognition, phone deactivation pruning, search, stack decoding. I.
On Supervised Learning From Sequential Data With Applications For Speech Recognition
, 1999
"... visualization of the problem to model human speech. A large number of example sequences of observation vectors (shown connected as continuous trajectories) depending on a given sequence of class labels, with each class representing for example a phoneme (here the name Keiko with given durations). In ..."
Abstract

Cited by 12 (1 self)
 Add to MetaCart
visualization of the problem to model human speech. A large number of example sequences of observation vectors (shown connected as continuous trajectories) depending on a given sequence of class labels, with each class representing for example a phoneme (here the name Keiko with given durations). In this synthetic example, the onedimensional target data would be represented poorly by a unimodal Gaussian distribution with a constant variance (which corresponds to using the squarederror objective function), which would average the two separate branches, indicated by the fat lines as the mean and constant variance of the single Gaussian. Compare this figure with Figure 3.10, Figure 3.11 and Figure 3.12 to see a subsequent improvement of the model.
Techniques for modelling Phonological Processes in Automatic Speech Recognition
, 2001
"... Declaration This dissertation is the result of my own work and includes nothing which is the outcome of work done in collaboration, except where stated. It has not been submitted in whole or part for a degree at any other university. The length of this thesis including footnotes and appendices does ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
Declaration This dissertation is the result of my own work and includes nothing which is the outcome of work done in collaboration, except where stated. It has not been submitted in whole or part for a degree at any other university. The length of this thesis including footnotes and appendices does not exceed 29,500 words and includes no more than 40 figures. 1 Systems which automatically transcribe carefully dictated speech are now commercially available, but their performance degrades dramatically when the speaking style of users becomes more relaxed or conversational. This dissertation focuses on techniques that aim to improve the robustness of statistical speech transcription systems to conversational speaking styles. The dissertation shows first that the performance degradation occuring as speech becomes more conversational is severe and is partially attributable to differences in the acoustic realizations of sentences. Hypothesizing that the quantifiably wider range of
Sequentially finding the nbest list in hidden markov models
 In Seventeenth International Joint Conference on Artificial Intelligence
, 2001
"... We propose a novel method to obtain the Nbest list of hypotheses in hidden Markov model (HMM). We show that the entire information needed to compute the Nbest list from the HMM trellis graph is encapsulated in entities that can be computed in a single forwardbackward iteration that usually yields ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We propose a novel method to obtain the Nbest list of hypotheses in hidden Markov model (HMM). We show that the entire information needed to compute the Nbest list from the HMM trellis graph is encapsulated in entities that can be computed in a single forwardbackward iteration that usually yields the most likely state sequence. The hypotheses list can then be extracted in a sequential manner from these entities without the need to refer back to the original data of the HMM. Furthermore, our approach can yield significant savings of computational time when compared to traditional methods. 1
An Efficient Algorithm for Sequentially finding the NBest List
, 1999
"... We propose a novel method to obtain the Nbest list of hypotheses produced by a speech recognizer. The proposed procedure is based on efficiently computation of the N most likely state sequences of a hidden Markov model. We show that the entire information needed to compute the Nbest list from the ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We propose a novel method to obtain the Nbest list of hypotheses produced by a speech recognizer. The proposed procedure is based on efficiently computation of the N most likely state sequences of a hidden Markov model. We show that the entire information needed to compute the Nbest list from the HMM trellis graph is encapsulated in entities that can be computed in a single forwardbackward iteration that usually yields the most likely state sequence. The hypotheses list can then be extracted in a sequential manner from these entities without the need to refer back to the original data of the HMM.
Sequentially finding theBest List in Hidden Markov Models
"... We propose a novel method to obtain thebest list of hypotheses in hidden Markov model (HMM). We show that the entire information needed to compute thebest list from the HMM trellis graph is encapsulated in entities that can be computed in a single forwardbackward iteration that usually yields the ..."
Abstract
 Add to MetaCart
We propose a novel method to obtain thebest list of hypotheses in hidden Markov model (HMM). We show that the entire information needed to compute thebest list from the HMM trellis graph is encapsulated in entities that can be computed in a single forwardbackward iteration that usually yields the most likely state sequence. The hypotheses list can then be extracted in a sequential manner from these entities without the need to refer back to the original data of the HMM. Furthermore, our approach can yield significant savings of computational time when compared to traditional methods. 1