Investigating the role of machine translated text in ASR domain adaptation: Unsupervised and semi-supervised methods

Cucu, Horia; Besacier, Laurent; Burileanu, Corneliu; Buzo, Andi

doi:10.1109/asru.2011.6163941

Cited by 9 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, by taking into consideration the previously transcribed letters in a word, rather than considering only the local letter context. Apart from the methods described here, another one that produces comparable results to decision trees and neural networks is statistical machine translation based LTS conversion which was applied to Romanian in [43].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

On letter to sound conversion for Romanian: A comparison of five algorithms

Toma

Birsan

Totir

et al. 2013

2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)

View full text Add to dashboard Cite

This paper presents an evaluation of 5 letter-tosound (LTS) systems for Romanian. The first is an expert system; three of them use automatic classification methods with decision trees, neural networks and support vector machines respectively and the fifth one uses pronunciation by analogy. All systems were trained and tested on the same database: a 15,517 words corpus built according to the SpeechDat specifications and a corpus consisting of the most frequent 4779 words in Romanian. The results show that decision trees and neural networks generate the best results for letter to sound conversion in Romanian.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Only recently, in [42] and in [43], bigger phonetic dictionaries were introduced, but these dictionaries were not available to us.…”

Section: Test Setupmentioning

confidence: 99%

On letter to sound conversion for Romanian: A comparison of five algorithms

Toma

Birsan

Totir

et al. 2013

2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)

View full text Add to dashboard Cite

show abstract

“…A "machine translation" system is trained based on an initial phonetic dictionary and afterwards this system is applied to convert any word to its phonetic form. Such an approach was, for example, proposed for Romanian language in Cucu et al (2011). Ghoshal et al (2009), Schlippe et al (2010Schlippe et al ( , 2013 describe automatic methods to produce pronunciation dictionaries using word-pronunciation pairs found in the World Wide Web.…”

Section: Bootstrapping G2p Using Mt Approachesmentioning

confidence: 99%

Automatic speech recognition for under-resourced languages: A survey

Besacier

Barnard

Karpov

et al. 2014

Speech Communication

Self Cite

393

195

View full text Add to dashboard Cite

Speech processing for under-resourced languages is an active field of research, which has experienced significant progress during the past decade. We propose, in this paper, a survey that focuses on automatic speech recognition (ASR) for these languages. The definition of under-resourced languages and the challenges associated to them are first defined. The main part of the paper is a literature review of the recent (last 8 years) contributions made in ASR for under-resourced languages. Examples of past projects and future trends when dealing with under-resourced languages are also presented. We believe that this paper will be a good starting point for anyone interested to initiate research in (or operational development of) ASR for one or several under-resourced languages. It should be clear, however, that many of the issues and approaches presented here, apply to speech technology in general (text-to-speech synthesis for instance).

show abstract

“…The indexed data are the transcriptions of the content data set using a phone recognizer. The multilingual acoustic model is obtained by adapting an acoustic model trained on Romanian language (previously developed in [22]) with the development data from the envisaged languages. The phone mapping is made using the International Phonetic Alphabet and a confusion matrix.…”

Section: But Spch G-dtw-devterms [17]mentioning

confidence: 99%