Morphology-based language modeling for conversational Arabic speech recognition

Kirchhoff, Katrin; Vergyri, Dimitra; Bilmes, Jeff; Duh, Kevin; Stolcke, Andreas

doi:10.1016/j.csl.2005.10.001

Cited by 77 publications

(49 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior research on applications of morphological analyzers has focused on machine translation, language modeling and speech recognition (Habash, 2008;Chahuneau et al, 2013a;Kirchhoff et al, 2006). Morphological analysis enables us to link together multiple inflections of the same root, thereby alleviating word sparsity common in morphologically rich languages.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Morphological Segmentation for Keyword Spotting

Narasimhan¹,

Karakos²,

Schwartz³

et al. 2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, stateof-the-art KWS systems do not use morphological information. In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations. Our experiments demonstrate that morphemes improve overall performance of KWS systems. Syllabic units, however, rival the performance of morphological units when used in KWS. By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Recent research has demonstrated that adding information about word structure increases the quality of translation systems and alleviates sparsity in language modeling (Chahuneau et al, 2013b;Habash, 2008;Kirchhoff et al, 2006;Stallard et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Morphological Segmentation for Keyword Spotting

Narasimhan¹,

Karakos²,

Schwartz³

et al. 2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…The final score for each hypothesis can be computed as a log-linear combination of the invoked scores. The weights of this combination can be optimized to minimize the WER [8]. For the weight optimization, we use "Amoeba" search which is available in SRILM toolkit [14].…”

Section: Score Combinationmentioning

confidence: 99%

“…The features can be generated based on linguistic methods as in [6], or via data driven approaches as in [7]. Possible approaches for incorporating word features into LMs are: stream-based LMs [8], class-based LMs [9] and factored LMs [10]. In stream-based LMs, a normal back-off N-gram model is built over a stream of word classes, where the stream consists of sequences of a single class type called class stream.…”

Section: Introductionmentioning

confidence: 99%

Investigations on the use of morpheme level features in Language Models for Arabic LVCSR

Mousa

Schlüter

Ney

2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

A major challenge for Arabic Large Vocabulary Continuous Speech Recognition (LVCSR) is the rich morphology of Arabic, which leads to high Out-of-vocabulary (OOV) rates, and poor Language Model (LM) probabilities. In such cases, the use of morphemes rather than full-words is considered a better choice for LMs. Thereby, higher lexical coverage and less LM perplexities are achieved. On the other side, an effective way to increase the robustness of LMs is to incorporate features of words into LMs. In this paper, we investigate the use of features derived for morphemes rather than words. Thus, we combine the benefits of both morpheme level and feature rich modeling. We compare the performance of streambased, class-based and Factored LMs (FLMs) estimated over sequences of morphemes and their features for performing Arabic LVCSR. A relative reduction of 3.9% in Word Error Rate (WER) is achieved compared to a word-based system.

show abstract

“…17, SI-2000, Maribor, Slovenia model (FLM). Such models were first proposed for speech recognition in Arabic languages [3], but they have also been adopted in statistical machine translation [4] and, more recently, in natural language generation [5].…”

Section: Introductionmentioning

confidence: 99%

Context-dependent factored language models

Donaj

KaăźIăź

2017

J AUDIO SPEECH MUSIC PROC.

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

Morphology-based language modeling for conversational Arabic speech recognition

Cited by 77 publications

References 27 publications

Morphological Segmentation for Keyword Spotting

Morphological Segmentation for Keyword Spotting

Investigations on the use of morpheme level features in Language Models for Arabic LVCSR

Context-dependent factored language models

Contact Info

Product

Resources

About