A danish text-to-speech system using a text normalizer based on morph analysis

A Nordic c o o p e r a t i v e p r o j e c t h a s been s t a r t e d t o d e v e l o p a tex t to speech d e v i c e f o r t h e Nordic languages. The development is based on t h e sys tem o r i g i n a l l y c r e a t e d i n Stockholm. Language s p e c i f i c f e a t u r e s have n e c e s s i t a t e d m o d i f i c a t i o n s o f t h e o r i g i n a l s t r u c t u r e . For Danish, t h i s p r i m a r i l y i n v o l v e s t h e i n c l u s i o n o f a morph b a s e d " t e x t n o r m a l i z i n g component". T h i s p a p e r p r e s e n t s t h e c o n s t r u c t i o n a n d f u n c t i o n o f t h e sys tem and a l s o d i s c u s s e s some p r e l i m i n a r y use o f t h e device . I n t r o d u c t i o n Speech s y n t h e s i s h a s b e e n a major l i n e o f r e s e a r c h i n o u r t w o d e p a r t m e n t s f o r s e v e r a l decades. I n Sweden, t h i s e f f o r t h a s r e s u l t e d i n a m u l t i l i n g u a l taxt to-speech sys tem (Car l son & Granstrom, 1986) , comm e r c i a l l y a v a i l a b l e t h r o u g h I n f o v o x AB. A j o i n t e f f o r t w i t h i n t h e p r o j e c t "A Nordic textto-speech system", f inanced by The Nordic Committee on D i s a b i l i t y , is a i m e d a t making t h i s d e v i c e a v a i l a b l e t o t h e handicapped i n t h e Nordic c o u n t r i e s . A l t h o q h t h e N o r d i c l a n g u a g e s are m u t u a l l y i n t e l l i g i b l e , D a n i s h p o s e s some s p e c i a l p r o b l e m s f o r a t e x t t o s p e e c h s y s t e m b e c a u s e t h e r e l a t i o n b e t w e e n t h e s t a n d a r d o r t o g r a p h y and p r o n u n c i a t i o n is r a t h e r complicated. To t a c k l e t h i s , w e have inc luded a unique component i n t h e sys tem t h a t t r a n s f o r m s words i n t o an i d e a l i z e d normal ized or thography. T h i s is accomplished through a morphological a n a l y s i s based on a set o f modera te ly l a r g e morph l e x i c a . With a l i m i t e d set o f r u l e s , t h e r e s u l t is t r a n s f o r m e d t o a p h o n e t i c t r a n s c r i p t i o n , i n c l u d i n g stress. I n a p h o n e t i c r u l e s c o m p o n e n t , s p e c i a l care h a s b e e n t a k e n t o r e a l i z e t h e p r o s o d i c s t r u c t u r e o f Danish which d i f f e r s c o n s i d e r a b l y from s t a n d a r d Swedish o r Norwegian. There are a l s o many o t h e r d i f f e r e n c e s i n s t r u c t u r e s u c h a s t h e a m p l e u s e o f " s t $ d " , a k i n d o f c r e a k y v o i c e unknown i n t h e o t h e r Nordic l anguages b u t which c o r r e s p o n d s r o u g h l y t o t h e t o n a l word a c c e n t 1 i n Swedish dnd Norwegian.