Abstract :
With the distribution of speech technology products all over the world, the fast and efficient portability to new target languages becomes a practical concern. The authors explore the relative effectiveness of adapting multilingual LVCSR systems to a new target language with limited adaptation data. For this purpose they 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 15 languages: Arabic, Mandarin and Shanghai Chinese, Croatian, English, French, German, Japanese, Korean, Portuguese, Russian, Spanish, Swedish, Tamil, and Turkish
Keywords :
decision trees; language translation; natural languages; speech recognition; Arabic; Croatian; English; French; German; GlobalPhone; Japanese; Korean; Mandarin; Portuguese; Russian; Shanghai Chinese; Spanish; Swedish; Tamil; Turkish; adaptation data; language adaptation; multilingual LVCSR systems; multilingual recognizers; polyphone decision tree specialization; polyphone decision tree specialization method; recognition results; speech recognition; speech technology product distribution; target language; target languages; Context modeling; Databases; Decision trees; Erbium; Hidden Markov models; Natural languages; Power system modeling; Speech; Target recognition; Training data;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
