Crosslingual transfer of source acoustic models to two different target languages
نویسندگان
چکیده
This paper presents the ongoing work on crosslingual speech recognition in the MASPER initiative. Source acoustic models were transferred to two different target languages – Hungarian and Slovenian. Beside the monolingual source acoustic models, also a semi-multilingual set was defined. An expert-knowledge approach and a data-driven method were applied for transfer. The crosslingual speech recognition results were used to analyse the robustness of different source acoustic models respective the language similarity influence.
منابع مشابه
Graphemes as basic units for crosslingual speech recognition
This paper presents our work on grapheme based crosslingual speech recognition carried out within the MASPER initiative. The performance of monolingual grapheme based acoustic models is compared to the performance of monolingual acoustic models based on phonemes. The transfer between source and target language was done using an expert knowledge approach. For the experiments, German, Spanish, Hu...
متن کاملBorrowing Language Resources for Development of Automatic Speech Recognition for Low- and Middle-Density Languages
In this paper we describe an approach that both creates crosslingual acoustic monophone model sets for speech recognition tasks and objectively predicts their performance without target-language speech data or acoustic measurement techniques. This strategy is based on a series of linguistic metrics characterizing the articulatory phonetic and phonological distances of target-language phonemes f...
متن کاملA non-acoustic approach to crosslingual speech recognition performance prediction
Crosslingual acoustic modeling is an effective technique for building acoustic models in the absence of native training data. A small amount of native speech data is still needed for verifying the crosslingual models by running an actual recognition test. In some very stringent yet realistic situations, however, even the test data may not be available. We introduce an algorithm that objectively...
متن کاملCrosslingual and bilingual speech recognition with Slovak and Czech speechdat-e databases
This paper presents the work on crosslingual and bilingual speech recognition carried out with SpeechDat databases for Czech and Slovak language. The work follows the MASPER initiative that was formed as a part of the COST 278 Action. In crosslingual experiments the expert-driven and the datadriven approaches were used for transferring monolingual source acoustic models to a target language. Th...
متن کاملThe COST 278 MASPER Initiative - Crosslingual Speech Recognition with Large Telephone Databases
This paper presents the work on crosslingual speech recognition carried out by the MASPER initiative that was formed as a part of the COST 278 Action. Two different approaches for transfering monolingual source acoustic models to a new language were compared. The first one was expert-driven, based on the IPA scheme. The second was data-driven, based on a crosslingual phoneme confusion matrix. G...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004