Large vocabulary continuous speech recognition of an inflected language using stems and endings

Rotovnik, Toma; Maučec, Mirjam Sepesy; Kačič, Zdravko

doi:10.1016/j.specom.2007.02.010

Cited by 33 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A statistical language model based on morphological decomposition of words into roots and inflectional groups which contain the inflectional features for each derived form has been proposed for morphological disambiguation of Turkish text [10]. Stems and endings have been used for language modeling for Turkish [11]- [13] and Slovenian [14]. Using linguistic information has the advantage that speech recognition output can be processed to filter invalid sequences of morphological units.…”

Section: Related Workmentioning

confidence: 99%

Morpholexical and Discriminative Language Models for Turkish Automatic Speech Recognition

Sak

Saraçlar

Güngör

2012

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

This paper introduces two complementary language modeling approaches for morphologically rich languages aiming to alleviate out-of-vocabulary (OOV) word problem and to exploit morphology as a knowledge source. The first model, morpholexical language model, is a generative -gram model, where modeling units are lexical-grammatical morphemes instead of commonly used words or statistical sub-words. This paper also proposes a novel approach for integrating the morphology into an automatic speech recognition (ASR) system in the finite-state transducer framework as a knowledge source. We accomplish that by building a morpholexical search network obtained by the composition of lexical transducer of a computational lexicon with a morpholexical language model. The second model is a linear reranking model trained discriminatively with a variant of the perceptron algorithm using morpholexical features. This variant of the perceptron algorithm, WER-sensitive perceptron, is shown to perform better for reranking -best candidates obtained with the generative model. We apply the proposed models in Turkish broadcast news transcription task and give experimental results. The morpholexical model leads to an elegant morphology-integrated search network with unlimited vocabulary. Thus, it is highly effective in alleviating OOV problem and improves the word error rate (WER) over word and statistical sub-word models by 1.8% and 0.4% absolute, respectively. The discriminatively trained morpholexical model further improves the WER of the system by 0.8% absolute.

show abstract

Section: Related Workmentioning

confidence: 99%

Morpholexical and Discriminative Language Models for Turkish Automatic Speech Recognition

Sak

Saraçlar

Güngör

2012

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…The lowest count of a vocabulary word was 36. The out-of-vocabulary rate on the evaluation set was 4.22%, which is significantly lower than for some other speech recognition systems built for highly inflectional Slovenian language (Žgank et al, 2001;Rotovnik et al, 2007). A possible reason for this is the usage of text corpora with speech transcriptions for language modelling.…”

Section: Language Modelling and Vocabularymentioning

confidence: 79%

Speech Recognition System of Slovenian Broadcast News

Maučec¹,

Žgank²

2011

Speech Technologies

View full text Add to dashboard Cite

“…The cause can be found in the rich morphology of such languages, which increases the need for larger vocabularies. It is estimated that inflectional languages need up to ten times larger vocabularies than English [1,2].…”

Section: Introductionmentioning

confidence: 99%

Context-dependent factored language models

Donaj

KaăźIăź

2017

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

The incorporation of grammatical information into speech recognition systems is often used to increase performance in morphologically rich languages. However, this introduces demands for sufficiently large training corpora and proper methods of using the additional information. In this paper, we present a method for building factored language models that use data obtained by morphosyntactic tagging. The models use only relevant factors that help to increase performance and ignore data from other factors, thus also reducing the need for large morphosyntactically tagged training corpora. Which data is relevant is determined at run-time, based on the current text segment being estimated, i.e., the context. We show that using a context-dependent model in a two-pass recognition algorithm, the overall speech recognition accuracy in a Broadcast News application improved by 1.73% relatively, while simpler models using the same data achieved only 0.07% improvement. We also present a more detailed error analysis based on lexical features, comparing first-pass and second-pass results.

show abstract

Large vocabulary continuous speech recognition of an inflected language using stems and endings

Cited by 33 publications

References 27 publications

Morpholexical and Discriminative Language Models for Turkish Automatic Speech Recognition

Morpholexical and Discriminative Language Models for Turkish Automatic Speech Recognition

Speech Recognition System of Slovenian Broadcast News

Context-dependent factored language models

Contact Info

Product

Resources

About