Unlimited vocabulary speech recognition with morph language models applied to Finnish

Hirsimäki, Teemu; Creutz, Mathias; Siivola, Vesa; Kurimo, Mikko; Virpioja, Sámi; Pylkkönen, Janne

doi:10.1016/j.csl.2005.07.002

Cited by 104 publications

(102 citation statements)

References 34 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…However, in agglutinative and highly inflected languages such as Finnish [6], Turkish [12], Estonian, Hungarian and Slavic languages, a simple stemming strategy is unlikely to perform well [4,6].…”

Section: Introductionmentioning

confidence: 99%

Automatic Semantic Subject Indexing of Web Documents in Highly Inflected Languages

Sinkkilä

Suominen

Hyvönen

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Structured semantic metadata about unstructured web documents can be created using automatic subject indexing methods, avoiding laborious manual indexing. A succesful automatic subject indexing tool for the web should work with texts in multiple languages and be independent of the domain of discourse of the documents and controlled vocabularies. However, analyzing text written in a highly inflected language requires word form normalization that goes beyond rule-based stemming algorithms. We have tested the state-of-the art automatic indexing tool Maui on Finnish texts using three stemming and lemmatization algorithms and tested it with documents and vocabularies of different domains. Both of the lemmatization algorithms we tested performed significantly better than a rule-based stemmer, and the subject indexing quality was found to be comparable to that of human indexers.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Semantic Subject Indexing of Web Documents in Highly Inflected Languages

Sinkkilä

Suominen

Hyvönen

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The decoder is a time-synchronous beam-pruned Viterbi token-pass system, and the language model is a morph-based growing n-gram model (Hirsimäki et al, 2009) trained on Finnish book and newspaper data with 145 million words. The vocabulary is in practice unlimited, since all words and word forms can be represented with statistical morphs (Hirsimäki et al, 2006).…”

Section: Baseline Systemmentioning

confidence: 99%

Comparing human and automatic speech recognition in a perceptual restoration experiment

Remes

López

Juvela

et al. 2016

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

Speech that has been distorted by introducing spectral or temporal gaps is still perceived as continuous and complete by human listeners, so long as the gaps are filled with additive noise of sufficient intensity. When such perceptual restoration occurs, the speech is also more intelligible compared to the case in which noise has not been added in the gaps. This observation has motivated so-called 'missing data' systems for automatic speech recognition (ASR), but there have been few attempts to determine whether such systems are a good model of perceptual restoration in human listeners. Accordingly, the current paper evaluates missing data ASR in a perceptual restoration task. We evaluated two systems that use a new approach to bounded marginalisation in the cepstral domain, and a bounded conditional mean imputation method. Both methods model available speech information as a clean-speech posterior distribution that is subsequently passed to an ASR system. The proposed missing data ASR systems were evaluated using distorted speech, in which spectro-temporal gaps were optionally filled with additive noise. Speech recognition performance of the proposed systems was compared against a baseline ASR system, and with human speech recognition performance on the same task. We conclude that missing data methods improve speech recognition performance in a manner that is consistent with perceptual restoration in human listeners.

show abstract

“…On account of this, each unit could have a closer counterpart in the other language (Spanish, in this case), and then, a more accurate translations could be obtained. In (Hirsimäki et al, 2006) an unsupervised algorithm for discovering word fragments was presented and evaluated in speech recognition for Finnish. The language model based on those units offered remarkable improvements over the traditional word-based language model.…”

Section: Morphological Approachmentioning

confidence: 99%

Joining linguistic and statistical methods for Spanish-to-Basque speech translation

Pérez

Torres

Casacuberta

2008

Speech Communication

View full text Add to dashboard Cite

To cite this version:Alicia Pérez, M. Inés Torres, Francisco Casacuberta. Joining linguistic and statistical methods for Spanish-to-Basque speech translation. Speech Communication, Elsevier : North-Holland, 2008, 50 (11-12) AbstractThe goal of this work is to develop a text and speech translation system from Spanish to Basque. This pair of languages shows quite odd characteristics as they differ extraordinarily in both morphology and syntax, thus, attractive challenges in machine translation are involved. Nevertheless, since both languages share official status in the Basque Country, the underlying motivation is not only academic but also practical.Finite-state transducers were adopted as basic translation models. The main contribution of this work involves the study of several techniques to improve probabilistic finite-state transducers by means of additional linguistic knowledge. Two methods to cope with both linguistics and statistics were proposed. The first one performed a morphological analysis in an attempt to benefit from atomic meaningful units when it comes to rendering the meaning from one language to the other. The second approach aimed at clustering words according to their syntactic role and used such phrases as translation unit. From the latter approach phrase-based finite-state transducers arose as a natural extension of classical ones.The models were assessed under a restricted domain task, very repetitive and with a small vocabulary. Experimental results shown that both morphological and syntactical approaches outperformed the baseline under different test sets and architectures for speech translation.

show abstract

Unlimited vocabulary speech recognition with morph language models applied to Finnish

Cited by 104 publications

References 34 publications

Automatic Semantic Subject Indexing of Web Documents in Highly Inflected Languages

Automatic Semantic Subject Indexing of Web Documents in Highly Inflected Languages

Comparing human and automatic speech recognition in a perceptual restoration experiment

Joining linguistic and statistical methods for Spanish-to-Basque speech translation

Contact Info

Product

Resources

About