9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

On the Use of a Multilingual Neural Network Front-End

Stefano Scanzio (1), Pietro Laface (1), Luciano Fissore (2), Roberto Gemello (2), Franco Mana (2)

(1) Politecnico di Torino, Italy; (2) Loquendo, Italy

This paper presents a front-end consisting of an Artificial Neural Network (ANN) architecture trained with multilingual corpora. The idea is to train an ANN front-end able to integrate the acoustic variations included in databases collected for different languages, through different channels, or even for specific tasks. This ANN front-end produces discriminant features that can be used as observation vectors for language or task dependent recognizers. The approach has been evaluated on three difficult tasks: recognition of non-native speaker sentences, training of a new language with a limited amount of speech data, and training of a model for car environment using a clean microphone corpus of the target language and data collected in car environment in another language.

Full Paper

Bibliographic reference.  Scanzio, Stefano / Laface, Pietro / Fissore, Luciano / Gemello, Roberto / Mana, Franco (2008): "On the use of a multilingual neural network front-end", In INTERSPEECH-2008, 2711-2714.