Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses

Ostendorf, Mari; Kannan, A.; Austin, S.; Kimball, Owen; Schwartz, Richard; Rohlíček, Ján

doi:10.3115/112405.112416

Cited by 79 publications

(40 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In our experimental systems, scores from various morphology-based language models are added. For score combination we use discriminative score combination framework (Beyerlein, 1998;Ostendorf et al, 1991). This approach aims at an optimal integration of independent sources of information in a log-linear model.…”

Section: Recognition Systemmentioning

confidence: 99%

Morphology-based language modeling for conversational Arabic speech recognition

Kirchhoff

Vergyri

Bilmes

et al. 2006

Computer Speech & Language

View full text Add to dashboard Cite

Language modeling for large-vocabulary conversational Arabic speech recognition is faced with the problem of the complex morphology of Arabic, which increases the perplexity and out-of-vocabulary rate. This problem is compounded by the enormous dialectal variability and differences between spoken and written language. In this paper we investigate improvements in Arabic language modeling by developing various morphology-based language models. We present four different approaches to morphology-based language modeling, including a novel technique called factored language models. Experimental results are presented for both rescoring and first-pass recognition experiments.

show abstract

Section: Recognition Systemmentioning

confidence: 99%

Morphology-based language modeling for conversational Arabic speech recognition

Kirchhoff

Vergyri

Bilmes

et al. 2006

Computer Speech & Language

View full text Add to dashboard Cite

show abstract

“…Though popular, it offers no guarantees about its approximation. In the category of multi-pass decoding, lattice and n-best list rescoring [13] are commonly used alternatives.…”

Section: Introductionmentioning

confidence: 99%

Discriminative segmental cascades for feature-rich phone recognition

Tang

Wang

Gimpel

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

View full text Add to dashboard Cite

Discriminative segmental models, such as segmental conditional random fields (SCRFs) and segmental structured support vector machines (SSVMs), have had success in speech recognition via both lattice rescoring and first-pass decoding. However, such models suffer from slow decoding, hampering the use of computationally expensive features, such as segment neural networks or other high-order features. A typical solution is to use approximate decoding, either by beam pruning in a single pass or by beam pruning to generate a lattice followed by a second pass. In this work, we study discriminative segmental models trained with a hinge loss (i.e., segmental structured SVMs). We show that beam search is not suitable for learning rescoring models in this approach, though it gives good approximate decoding performance when the model is already well-trained. Instead, we consider an approach inspired by structured prediction cascades, which use max-marginal pruning to generate lattices. We obtain a highaccuracy phonetic recognition system with several expensive feature types: a segment neural network, a second-order language model, and second-order phone boundary features.Index Terms-segmental conditional random field, structured prediction cascades, phone recognition, segment neural network, beam search

show abstract

“…The grammar scale must be optimized based on the task and the quality of the LM using a development set to ensure good performance (Wang et al, 2002;Ostendorf et al, 1991;Rayner et al, 1994).…”

Section: Pruning Conclusionmentioning

confidence: 99%

The effect of pruning and compression on graphical representations of the output of a speech recognizer

Liu

Harper

Johnson

et al. 2003

Computer Speech & Language

View full text Add to dashboard Cite

Large vocabulary continuous speech recognition can benefit from an efficient data structure for representing a large number of acoustic hypotheses compactly. Word graphs or lattices have been chosen as such an efficient interface between acoustic recognition engines and subsequent language processing modules. This paper first investigates the effect of pruning during acoustic decoding on the quality of word lattices and shows that by combining different pruning options (at the model level and word level), we can obtain word lattices with comparable accuracy to the original lattices and a manageable size. In order to use the word lattices as the input for a post-processing language module, they should preserve the target hypotheses and their scores while being as small as possible. In this paper, we introduce a word graph compression algorithm that significantly reduces the number of words in the graphical representation without eliminating utterance hypotheses or distorting their acoustic scores. We compare this word graph compression algorithm with several other lattice size-reducing approaches and demonstrate the relative strength of the new word graph compression algorithm for decreasing the number of words in the representation. Experiments are conducted across corpora and vocabulary sizes to determine the consistency of the pruning and compression results.

show abstract

Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses

Cited by 79 publications

References 16 publications

Morphology-based language modeling for conversational Arabic speech recognition

Morphology-based language modeling for conversational Arabic speech recognition

Discriminative segmental cascades for feature-rich phone recognition

The effect of pruning and compression on graphical representations of the output of a speech recognizer

Contact Info

Product

Resources

About