OpenFst: A General and Efficient Weighted Finite-State Transducer Library

Allauzen, Cyril; Riley, Michael; Schalkwyk, Johan; Skut, Wojciech; Mohri, Mehryar

doi:10.1007/978-3-540-76336-9_3

Cited by 395 publications

(279 citation statements)

References 10 publications

Supporting

Mentioning

276

Contrasting

Unclassified

Order By: Relevance

“…At this point, we are able to extract a probability distribution over possible character selections by performing weight pushing to the end of the machine, and then examining the final set of arcs in F OCLM . All of these FST operations are implemented with the OpenFst (Allauzen et al, 2007) and OpenGRM-NGRAM libraries.…”

Section: Methodology 21 Overviewmentioning

confidence: 99%

Proceedings of the Second Workshop on Subword/Character LEvel Models

2018

View full text Add to dashboard Cite

ii Introduction Traditional NLP starts with a hand-engineered layer of representation, the level of tokens or words. A tokenization component first breaks up the text into units using manually designed rules. Tokens are then processed by components such as word segmentation, morphological analysis and multiword recognition. The heterogeneity of these components makes it hard to create integrated models of both structure within tokens (e.g., morphology) and structure across multiple tokens (e.g., multi-word expressions). This approach can perform poorly (i) for morphologically rich languages, (ii) for noisy text, (iii) for languages in which the recognition of words is difficult and (iv) for adaptation to new domains; and (v) it can impede the optimization of preprocessing in end-to-end learning.The workshop provides a forum for discussing recent advances as well as future directions on sub-word and character-level natural language processing and representation learning that address these problems. Topics of Interest:• tokenization-free models• character-level machine translation• character-ngram information retrieval• transfer learning for character-level models• models of within-token and cross-token structure• NL generation (of words not seen in training etc)• out of vocabulary words• morphology and segmentation• relationship b/w morphology and character-level models• stemming and lemmatization • inflection generation• orthographic productivity• form-meaning representations• true end-to-end learning AbstractNeural machine translation has achieved impressive results in the last few years, but its success has been limited to settings with large amounts of parallel data. One way to improve NMT for lower-resource settings is to initialize a word-based NMT model with pretrained word embeddings. However, rare words still suffer from lower quality word embeddings when trained with standard word-level objectives. We introduce word embeddings that utilize morphological resources, and compare to purely unsupervised alternatives. We work with Arabic, a morphologically rich language with available linguistic resources, and perform Ar-to-En MT experiments on a small corpus of TED subtitles. We find that word embeddings utilizing subword information consistently outperform standard word embeddings on a word similarity task and as initialization of the source word embeddings in a low-resource NMT system.

show abstract

Section: Methodology 21 Overviewmentioning

confidence: 99%

Proceedings of the Second Workshop on Subword/Character LEvel Models

2018

View full text Add to dashboard Cite

show abstract

“…All possible command words or expressions have an entry in the CFG, for modelling standard phraseology and often used deviation forms. Each semantic slot for the command is tagged in the CFG, and hence, transducing [21] a transcript hypothesis from the ASR over the CFG results in an XML tagged version as follows (using the previous example): hello <callsign> <airline> lufthansa </airline> <flightnumber> eight echo kilo </flightnumber> </callsign> start <commands> <command="reduce"> reduce your speed to <speed> two two zero </speed> knots </command> </commands>. If transductions fail (due to a deviation in phraseology not modelled by the CFG or due to ASR errors), the command extractor returns "NO_CALLSIGN" if the callsign is missed, and "NO_CONCEPT", if the command word or the command attribute could not be recovered.…”

Section: Concept and Command Extractionmentioning

confidence: 99%

Semi-Supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control

Srinivasamurthy¹,

Motlíček²,

Himawan³

et al. 2017

Interspeech 2017

View full text Add to dashboard Cite

Automatic Speech Recognition (ASR) can introduce higher levels of automation into Air Traffic Control (ATC), where spoken language is still the predominant form of communication. While ATC uses standard phraseology and a limited vocabulary, we need to adapt the speech recognition systems to local acoustic conditions and vocabularies at each airport to reach optimal performance. Due to continuous operation of ATC systems, a large and increasing amount of untranscribed speech data is available, allowing for semi-supervised learning methods to build and adapt ASR models. In this paper, we first identify the challenges in building ASR systems for specific ATC areas and propose to utilize out-of-domain data to build baseline ASR models. Then we explore different methods of data selection for adapting baseline models by exploiting the continuously increasing untranscribed data. We develop a basic approach capable of exploiting semantic representations of ATC commands. We achieve relative improvement in both word error rate (23.5%) and concept error rates (7%) when adapting ASR models to different ATC conditions in a semi-supervised manner.

show abstract

“…The lattices of all the utterances in the eval set are converted from individual finite state transducers (FST) output by Kaldi to a single generalized factor transducer structure in which the start-time, end-time and lattice posterior probability of each word token in every lattice is stored as a 3-dimensional cost associated with that instance of the word. This factor transducer is, in essence, an inverted index of all word sequences seen in the collection of eval set lattices, and permits further manipulation easily using the Google OpenFST tools [19]. Interested readers are referred to [18] for details.…”

Section: Openfst-based Kws System Descriptionmentioning

confidence: 99%

Quantifying the value of pronunciation lexicons for keyword search in lowresource languages

Chen

Khudanpur

Povey

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This paper quantifies the value of pronunciation lexicons in large vocabulary continuous speech recognition (LVCSR) systems that support keyword search (KWS) in low resource languages. Stateof-the-art LVCSR and KWS systems are developed for conversational telephone speech in Tagalog, and the baseline lexicon is augmented via three different grapheme-to-phoneme models that yield increasing coverage of a large Tagalog word-list. It is demonstrated that while the increased lexical coverage -or reduced out-of-vocabulary (OOV) rate -leads to only modest (ca 1%-4%) improvements in word error rate, the concomitant improvements in actual term weighted value are as much as 60%. It is also shown that incorporating the augmented lexicons into the LVCSR system before indexing speech is superior to using them post facto, e.g., for approximate phonetic matching of OOV keywords in pre-indexed lattices. These results underscore the disproportionate importance of automatic lexicon augmentation for KWS in morphologically rich languages, and advocate for using them early in the LVCSR stage.Index Terms-Speech Recognition, Keyword Search, Information Retrieval, Morphology, Speech Synthesis LOW-RESOURCE KEYWORD SEARCHThanks in part to the falling costs of storage and transmission, large volumes of speech such as oral history archives [1, 2] and on-line lectures [3,4] are now easily accessible by large user populations via the world wide web. Unlike the text-web, however, searching speech using keywords continues to be a challenging problem. Manually transcribing the speech is often prohibitively expensive. Automatic keyword search (KWS) systems are able to address the problem in some cases, but not in others, because high performance KWS systems, in turn, rely on underlying large vocabulary continuous speech recognition (LVCSR) systems that are also expensive to develop. Good LVCSR systems utilize statistical acoustic-and language-models trained from large quantities of transcribed speech and "conversational" text in the search domain, and manually crafted pronunciation lexicons with good coverage of the collection.We are interested in improving KWS performance in a low resource setting, i.e. where some resources are available to developThe authors, listed here in alphabetical order, were supported by DARPA BOLT contract Nō HR0011-12-C-0015, and IARPA BABEL contract Nō W911NF-12-C-0015. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of DARPA, IARPA, DoD/ARL or the U.S. Government.an LVCSR system -such as 10 hours of transcribed speech corresponding to about 100K words of transcribed text, and a pronunciation lexicon that covers the words in the training data -but accuracy is sufficiently low that considerable improvement in K...

show abstract

OpenFst: A General and Efficient Weighted Finite-State Transducer Library

Cited by 395 publications

References 10 publications

Proceedings of the Second Workshop on Subword/Character LEvel Models

Proceedings of the Second Workshop on Subword/Character LEvel Models

Semi-Supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control

Quantifying the value of pronunciation lexicons for keyword search in lowresource languages

Contact Info

Product

Resources

About