Compound words in large-vocabulary German speech recognition systems

Berton, André; Fetter, Pablo; Regel-Brietzmann, Peter

doi:10.1109/icslp.1996.607814

Cited by 27 publications

(17 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Yang et al [1998], the elements of the lexicon can be any "segment patterns" extracted from the training corpus with the goal of minimizing the overall perplexity. The same perplexity-based metric is also used by Giachin [1995] and Berton et al [1996] to add and remove lexicon items. However, in practice, finding an optimal lexicon on the basis of perplexity estimates is very computationally expensive.…”

Section: Lexicon Construction From Corpusmentioning

confidence: 99%

Toward a unified approach to statistical language modeling for Chinese

Gao

Goodman

et al. 2002

ACM Transactions on Asian Language Information Processing

View full text Add to dashboard Cite

This article presents a unified approach to Chinese statistical language modeling (SLM). Applying SLM techniques like trigram language models to Chinese is challenging because (1) there is no standard definition of words in Chinese; (2) word boundaries are not marked by spaces; and (3) there is a dearth of training data. Our unified approach automatically and consistently gathers a high-quality training data set from the Web, creates a high-quality lexicon, segments the training data using this lexicon, and compresses the language model, all by using the maximum likelihood principle, which is consistent with trigram model training. We show that each of the methods leads to improvements over standard SLM, and that the combined method yields the best pinyin conversion result reported.

show abstract

Section: Lexicon Construction From Corpusmentioning

confidence: 99%

Toward a unified approach to statistical language modeling for Chinese

Gao

Goodman

et al. 2002

ACM Transactions on Asian Language Information Processing

View full text Add to dashboard Cite

show abstract

“…They modeled the data-driven variants in both the dictionary and the language model. Berton et al (1996) introduced a method for handling the components of compounds rather than the compounds themselves. They proposed a method to decompose the OOV compound words to words already in the lexicon.…”

Section: Literature Reviewmentioning

confidence: 99%

Toward enhanced Arabic speech recognition using part of speech tagging

AbuZeina

Al-Khatib

Elshafei

et al. 2011

Int J Speech Technol

View full text Add to dashboard Cite

One major source of suboptimal performance in automatic continuous speech recognition systems is misrecognition of small words. In general, errors resulting from small words are much more than errors resulting from long words. Therefore, compounding some words (small or long) to produce longer words is welcome by speech recognition decoders. In this paper, we present a novel approach to artificially generate compound words using part of speech tagging. For this purpose, we consider two cases in Arabic speech where two words are pronounced without a silence period in between: a noun followed by an adjective, and a preposition followed by any word. To collect the candidate compound words, we use Stanford Arabic tagger to tag all words in our baseline transcription corpus. Then, compound words are generated whenever any of the two cases occur in a sequence of two words. The unique compound words are then added to the expanded pronunciation dictionary, as well as to the language model. Using Sphinx 3, we test the proposed method for a 5.4 hours speech corpus of modern standard Arabic. The results show a significant improvement, as the word error rate is reduced by 2.39%.

show abstract

“…An example of this is Berton, Fetter, and Regel-Brietzmann (1996), who extended the word graphs output by a German speech recognizer with possible compounds by combining edges of words during a lexical search. The final hypotheses were then identified from the graph using dynamic programming techniques.…”

Section: Related Workmentioning

confidence: 99%

Generation of Compound Words in Statistical Machine Translation into Compounding Languages

Stymne

Cancedda

Ahrenberg

2013

Computational Linguistics

View full text Add to dashboard Cite

In this article we investigate statistical machine translation (SMT) into Germanic languages, with a focus on compound processing. Our main goal is to enable the generation of novel compounds that have not been seen in the training data. We adopt a split-merge strategy, where compounds are split before training the SMT system, and merged after the translation step. This approach reduces sparsity in the training data, but runs the risk of placing translations of compound parts in non-consecutive positions. It also requires a postprocessing step of compound merging, where compounds are reconstructed in the translation output. We present a method for increasing the chances that components that should be merged are translated into contiguous positions and in the right order and show that it can lead to improvements both by direct inspection and in terms of standard translation evaluation metrics. We also propose several new methods for compound merging, based on heuristics and machine learning, which outperform previously suggested algorithms. These methods can produce novel compounds and a translation with at least the same overall quality as the baseline. For all subtasks we show that it is useful to include part-of-speech based information in the translation process, in order to handle compounds

show abstract

Compound words in large-vocabulary German speech recognition systems

Cited by 27 publications

References 2 publications

Toward a unified approach to statistical language modeling for Chinese

Toward a unified approach to statistical language modeling for Chinese

Toward enhanced Arabic speech recognition using part of speech tagging

Generation of Compound Words in Statistical Machine Translation into Compounding Languages

Contact Info

Product

Resources

About