In-service adaptation of multilingual hidden-Markov-models

Bub, Udo; Köhler, Joachim; Imperl, Bojan

doi:10.1109/icassp.1997.596222

Cited by 20 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research in this area investigates whether cross-language transfer between two languages of the same family performs better than across family borders (Constantinescu and Chollet, 1997), and whether the number of languages used for training the original acoustic transfer models influences the performance on the target language (Gokcen and Gokcen, 1997;Schultz and Waibel, 1998b). Some results indicate a relation between language similarity and cross-language performance (Bub et al, 1997;Constantinescu and Chollet, 1997). Furthermore, others (Bub et al, 1997) and our experiments have clearly shown that multilingual transfer models outperform monolingual ones (Schultz and Waibel, 1998a).…”

Section: Language Adaptive Acoustic Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Language-independent and language-adaptive acoustic modeling for speech recognition

Schultz

Waibel

2001

Speech Communication

329

222

View full text Add to dashboard Cite

With the distribution of speech technology products all over the world, the portability to new target languages becomes a practical concern. As a consequence our research focuses on the question of how to port LVCSR systems in a fast and efficient way. More specifically we want to estimate acoustic models for a new target language using speech data from varied source languages, but only limited data from the target language. For this purpose we introduce different methods for multilingual acoustic model combination and a polyphone decision tree specialization procedure. Recognition results using language dependent, independent and language adaptive acoustic models are presented and discussed in the framework of our GlobalPhone project which investigates LVCSR systems in 15 languages.

show abstract

Section: Language Adaptive Acoustic Modelingmentioning

confidence: 99%

“…Some results indicate a relation between language similarity and cross-language performance (Bub et al, 1997;Constantinescu and Chollet, 1997). Furthermore, others (Bub et al, 1997) and our experiments have clearly shown that multilingual transfer models outperform monolingual ones (Schultz and Waibel, 1998a). …”

Section: Language Adaptive Acoustic Modelingmentioning

confidence: 99%

Language-independent and language-adaptive acoustic modeling for speech recognition

Schultz

Waibel

2001

Speech Communication

329

222

View full text Add to dashboard Cite

show abstract

“…We address three aspects of research due to the amount of available data in the target language: Cross-language transfer refers to the technique where a system developed in one language is applied to recognize another language without using any training data of the new language. Experimental results indicate a relation between language similarity and cross-language performance [1], [2]. Furthermore it is shown that multilingual acoustic transfer models perform better than monolingual ones [2], [3].…”

Section: Introductionmentioning

confidence: 99%

“…Experimental results indicate a relation between language similarity and cross-language performance [1], [2]. Furthermore it is shown that multilingual acoustic transfer models perform better than monolingual ones [2], [3]. The key idea in the bootstrapping approach is to initialize a recognizer in the target language by using acoustic models from other languages as seed models.…”

Section: Introductionmentioning

confidence: 99%

Polyphone decision tree specialization for language adaptation

Schultz

Waibel

2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)

View full text Add to dashboard Cite

With the distribution of speech technology products all over the world, the fast and efficient portability to new target languages becomes a practical concern. In this paper we explore the relative effectiveness of adapting multilingual LVCSR systems to a new target language with limited adaptation data. For this purpose we introduce a polyphone decision tree specialization method. Several recognition results are presented based on mono-and multilingual recognizers. These recognizers are developed in the framework of the project GlobalPhone. In this project we investigate speech recognition in the 15 languages Arabic, Mandarin and Shanghai

show abstract

“…In a different experiment the phonetically rich sentences of the German SpeechDat(M) database proved to be useful for training of balanced acoustic models for general German [15]. These models are necessary for recognition of new tasks that lack enough specific training data.…”

Section: Scientific and Com M Ercial Relevancementioning

confidence: 99%

European speech databases for telephone applications

Höge

Tropf

Winski

et al.

1997 IEEE International Conference on Acoustics, Speech, and Signal Processing

View full text Add to dashboard Cite

The SpeechDat project aims to produce speech databases for all official languages of the European Union and some major dialectal variants and minority languages resulting in 28 speech databases. They will be recorded over fixed and mobile telephone networks. This will provide a realistic basis for training and assessment of both isolated and continuous-speech utterances, em ploying whole-word or subword approaches, and thus can be used for developing voice driven teleservices in cluding speaker verification. The specification of the databases has been developed jointly, and is essentially the same for each language to facilitate dissemination and use. There will be a controlled variation among the speakers concerning sex, age, dialect, environment of call etc. The validation of all databases will be carried out centrally. The SpeechDat databases will be trans ferred to ELRA for distribution. Next databases to be recorded will cover East European languages.

show abstract

In-service adaptation of multilingual hidden-Markov-models

Cited by 20 publications

References 9 publications

Language-independent and language-adaptive acoustic modeling for speech recognition

Language-independent and language-adaptive acoustic modeling for speech recognition

Polyphone decision tree specialization for language adaptation

European speech databases for telephone applications

Contact Info

Product

Resources

About