Stochastic automata for language modeling

Riccardi, Giuseppe; Pieraccini, Roberto; Bocchieri, Enrico

doi:10.1006/csla.1996.0014

Cited by 73 publications

(53 citation statements)

References 22 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem could be solved by setting N to a larger value, but this would increase computation cost substantially. Another approach is to use probabilistic finite-state grammars for the ASR language models [4]. Although this would improve ASR accuracy, some utterances might be misrecognized due to their structural constraints.…”

Section: Conceptmentioning

confidence: 99%

Automatic Allocation of Training Data for Speech Understanding Based on Multiple Model Combinations

Komatani

Nakano

Katsumaru

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThe optimal way to build speech understanding modules depends on the amount of training data available. When only a small amount of training data is available, effective allocation of the data is crucial to preventing overfitting of statistical methods. We have developed a method for allocating a limited amount of training data in accordance with the amount available. Our method exploits rule-based methods for when the amount of data is small, which are included in our speech understanding framework based on multiple model combinations, i.e., multiple automatic speech recognition (ASR) modules and multiple language understanding (LU) modules, and then allocates training data preferentially to the modules that dominate the overall performance of speech understanding. Experimental evaluation showed that our allocation method consistently outperforms baseline methods that use a single ASR module and a single LU module while the amount of training data increases. key words: spoken dialogue system, language understanding, rapid prototyping, limited amount of training data

show abstract

Section: Conceptmentioning

confidence: 99%

Automatic Allocation of Training Data for Speech Understanding Based on Multiple Model Combinations

Komatani

Nakano

Katsumaru

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The word trigram model and phone 5-gram language models in these recognizers were constructed using the stochastic language modeling techniques described by Riccardi, Pieraccini, and Bocchieri (1996).…”

Section: Utterance Featuresmentioning

confidence: 99%

Online Multiclass Learning with k-Way Limited Feedback and an Application to Utterance Classification

Alshawi

2005

Mach Learn

View full text Add to dashboard Cite

Abstract. This paper introduces a setting for multiclass online learning with limited feedback and its application to utterance classification. In this learning setting, a parameter k limits the number of choices presented for selection by the environment (e.g. by the user in the case of an interactive spoken system) during each trial of the online learning sequence. New versions of standard additive and multiplicative weight update algorithms for online learning are presented that are more suited to the limited feedback setting, while sharing the efficiency advantages of the standard ones. The algorithms are evaluated on an utterance classification task in two domains. In this utterance classification task, no training material for the domain is provided (for training the speech recognizer or classifier) prior to the start of online learning. We present experiments on the effect of varying k and the weight update algorithms on the learning curve for online utterance classification. In these experiments, the new online learning algorithms improve classification accuracy compared with the standard ones. The methods presented are directly relevant to applications such as building call routing systems that adapt from feedback rather than being trained in batch mode.

show abstract

“…The most successful parsing algorithm for finding the most likely sequence of spoken words is Viterbi decoding along with beam search [14]. A unified formalism for building a wide class of language models are the variable multi-gram stochastic automata [12].…”

Section: Introductionmentioning

confidence: 99%

Inference and Learning in Stochastic Automata

Zimmermann¹

2017

Int. J. of Pure and Appl. Math.

View full text Add to dashboard Cite

Machine learning provides algorithms that can learn from data and make inferences or predictions on data. Stochastic automata are a class of input/output devices which can model components in machine learning scenarios. In this paper, we provide an inference algorithm for stochastic automata which is related to the Viterbi algorithm. Moreover, we specify a learning algorithm using the expectation-maximization technique and describe a more efficient implementation which is related to the Baum-Welch algorithm.

show abstract

Stochastic automata for language modeling

Cited by 73 publications

References 22 publications

Automatic Allocation of Training Data for Speech Understanding Based on Multiple Model Combinations

Automatic Allocation of Training Data for Speech Understanding Based on Multiple Model Combinations

Online Multiclass Learning with k-Way Limited Feedback and an Application to Utterance Classification

Inference and Learning in Stochastic Automata

Contact Info

Product

Resources

About