Tony Robinson, Mike Hochberg, Steve Renals
This chapter was written in 1994. Further advances have been made such as: context- dependent phone modelling; forward-backward training and adaptation using linear input transformations. This...
Mike Hochberg, Ciro Martins, Steve Renals, Tony Robinson
It is well known that recognition performance degrades significantly when moving from a speakerdependent to a speaker-independent system. Traditional hidden Markov model (HMM) systems have...
Start-synchronous search for large vocabulary continuous speech recognition. (1999)
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 phone-level...
Start-synchronous search for large vocabulary continuous speech recognition. (1999)
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 phone-level...
Start-Synchronous Search for Large Vocabulary Continuous Speech Recognition (1997)
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 phone-level...
Efficient evaluation of the LVCSR search space using the NOWAY decoder (1996)
This article further develops and analyses the large vocabulary continuous speech recognition (LVCSR) search strategy reported by Renals and Hochberg (see Proc. ICASSP '95, p.596-9, 1995). In...
Efficient evaluation of the LVCSR search space using the NOWAY decoder (1996)
This article further develops and analyses the large vocabulary continuous speech recognition (LVCSR) search strategy reported by Renals and Hochberg (see Proc. ICASSP '95, p.596-9, 1995). In...
Efficient Evaluation Of The Lvcsr Search Space Using The Noway Decoder (1996)
This work further develops and analyses the large vocabulary continuous speech recognition (LVCSR) search strategy reported at ICASSP-95 [1]. In particular, the posteriorbased phone deactivation...
Efficient search using posterior phone probability estimates. (1995)
In this paper we present a novel, efficient search strategy for large vocabulary continuous speech recognition (LVCSR). The search algorithm, based on stack decoding, uses posterior phone probability...
The 1994 Abbot hybrid connectionist-HMM large vocabulary recognition system. (1995)
Hochberg, Mike, Cook, Gary, Renals, Steve, Robinson, Tony, Schechtman, R
Recent improvements to the Abbot large vocabulary CSR system. (1995)
Hochberg, Mike, Renals, Steve, Robinson, Tony, Cook, Gary
ABBOT is the hybrid connectionist-hidden Markov model (HMM) large-vocabulary continuous speech recognition (CSR) system developed at Cambridge University. This system uses a recurrent network to...
Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System (1995)
Neto, Joao, Almeida, Luis, Hochberg, Mike, Martins, Ciro, Nunes, Luis, Renals, Steve, ...
It is well known that recognition performance degrades significantly when moving from a speaker-dependent to a speaker-independent system. Traditional hidden Markov model (HMM) systems have...
Efficient search using posterior phone probability estimates. (1995)
In this paper we present a novel, efficient search strategy for large vocabulary continuous speech recognition (LVCSR). The search algorithm, based on stack decoding, uses posterior phone probability...
The 1994 Abbot hybrid connectionist-HMM large vocabulary recognition system. (1995)
Hochberg, Mike, Cook, Gary, Renals, Steve, Robinson, Tony, Schechtman, R
Recent improvements to the Abbot large vocabulary CSR system. (1995)
Hochberg, Mike, Renals, Steve, Robinson, Tony, Cook, Gary
ABBOT is the hybrid connectionist-hidden Markov model (HMM) large-vocabulary continuous speech recognition (CSR) system developed at Cambridge University. This system uses a recurrent network to...
Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System (1995)
Neto, Joao, Almeida, Luis, Hochberg, Mike, Martins, Ciro, Nunes, Luis, Renals, Steve, ...
It is well known that recognition performance degrades significantly when moving from a speaker-dependent to a speaker-independent system. Traditional hidden Markov model (HMM) systems have...
Efficient Search Using Posterior Phone Probability Estimates (1995)
In this paper we present a novel, efficient search strategy for large vocabulary continuous speech recognition (LVCSR). The search algorithm, based on stack decoding, uses posterior phone probability...
Context-Dependent Classes in a Hybrid Recurrent Network-HMM Speech Recognition System (1995)
Dan Kershaw, Tony Robinson, Mike Hochberg
A method for incorporating context-dependent phone classes in a connectionist-HMM hybrid speech recognition system is introduced. A modular approach is adopted, where single-layer networks...
Decoder Technology For Connectionist Large Vocabulary Speech Recognition (1995)
The search problem in large vocabulary continuous speech recognition (LVCSR) is to locate the most probable string of words for a spoken utterance given the acoustic signal and a set of sentence...
Connectionist model combination for large vocabulary speech recognition (1994)
Hochberg, Mike, Cook, Gary, Renals, Steve, Robinson, Tony
Reports in the statistics and neural networks literature have expounded the benefits of merging multiple models to improve classification and prediction performance. The Cambridge University...
Connectionist model combination for large vocabulary speech recognition (1994)
Hochberg, Mike, Cook, Gary, Renals, Steve, Robinson, Tony
Reports in the statistics and neural networks literature have expounded the benefits of merging multiple models to improve classification and prediction performance. The Cambridge University...
IPA: improved phone modelling with recurrent neural networks (1994)
Robinson, Tony, Hochberg, Mike, Renals, Steve
This paper describes phone modelling improvements to the hybrid connectionist-hidden Markov model speech recognition system developed at Cambridge University. These improvements are applied to phone...
IPA: improved phone modelling with recurrent neural networks (1994)
Robinson, Tony, Hochberg, Mike, Renals, Steve
This paper describes phone modelling improvements to the hybrid connectionist-hidden Markov model speech recognition system developed at Cambridge University. These improvements are applied to phone...
Learning temporal dependencies in connectionist speech recognition (1994)
Renals, Steve, Hochberg, Mike, Robinson, Tony
Hybrid connectionist/HMM systems model time using both a Markov chain and through properties of a connectionist network. In this paper, we discuss the nature of the time dependence currently employed...
Learning temporal dependencies in connectionist speech recognition (1994)
Renals, Steve, Hochberg, Mike, Robinson, Tony
Hybrid connectionist/HMM systems model time using both a Markov chain and through properties of a connectionist network. In this paper, we discuss the nature of the time dependence currently employed...
Using Gamma Filters To Model Temporal Dependencies In Speech (1994)
Hybrid systems which use connectionist networks to estimate the output probabilities of a hidden Markov model represent time both at the network level and the Markov chain level. In this paper we...
Start-Synchronous Search for Large Vocabulary Continuous Speech Recognition
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 phone-level...