deBas: a sinhala Interactive voice response (IVR) system
JD Nallathamby, Kkr Kariyawasam, HD Pullaperuma, DC Vithana, Sumedha D. Jayasena · 2011
A l t h o u g h t h e r e a r e w i d e l y used I n t e r a c t i v e Voice Response (IVR) systems i n many l a n g u a g e s t o d a y , t h e r e is no S i n h a l a l a n g u a g e IVR system yet. This p a p e r t a l k s a b o u t deBas I V R : a c o m p l e t e S i n h a l a I V R w i t h a u t o m a t i c speech r e c o g n i t i o n (ASR) a n d text-to-speech (TTS) synthesis modules t h a t w o r k i n c o m p l i a n c e w i t h M e d i a Resource C o n t r o l P r o t o c o l (MRCP). I t discusses some b a c k g r o u n d l i t e r a t u r e , t h e process t a k e n , t h e o v e r a l l d e s i g n a n d i m p l e m e n t a t i o n aspects a n d t h e f u t u r e w o r k t h a t c a n be c a r r i e d o u t i n t h i s a r e a . I n t h e ASR component, t r a i n i n g t h e a c o u s t i c m o d e l is done w i t h S p h i n x T r a i n , a n d d e c o d i n g w i t h P o c k e t S p h i n x , w h i c h a r e based o n H i d d e n M a r k o v M o d e l s (HMM). I n t h e TTS component, A M o R A S i n h a l a TTS k n o w l e d g e base is used, w h i c h uses F e s t i v a l speech synthesis e n g i n e a n d a f e m a l e d i p h o n i c v o i c e , b u i l t u s i n g Festvox v o i c e b u i l d i n g t o o l s . A s t e r i s k is used as t h e IVR gateway a n d d i a l p l a n i n t e r p r e t e r . M R C P v 2 p r o t o c o l has been f o l l o w e d i n d e v e l o p i n g t h e speech r e s o u r c e s , w h i c h uses Session I n i t i a t i o n P r o t o c o l (SIP) f o r e s t a b l i s h i n g c o n t r o l l e d c o n n e c t i o n s t o e x t e r n a l m e d i a s t r e a m i n g devices a n d R e a l t i m e T r a n s p o r t P r o t o c o l (RTP) f o r m e d i a d e l i v e r y . The l a n g u a g e m o d e l of t h e ASR c o m p o n e n t has been r e s t r i c t e d t o d i g i t s f r o m 0-9 t h a t a r e c o m m o n l y used i n IVR systems a n d t h e set of w o r d s used f o r o u r demo a p p l i c a t i o n . The W o r d E r r o r R a t e a n d t h e S e n t e n c e E r r o r Rate of t h e ASR c o m p o n e n t a r e r e p o r t e d t o be 3 1 . 4 % a n d 5 4 % r e s p e c t i v e l y , as o b s e r v e d i n o u r e x p e r i m e n t s . I n a d d i t i o n t o these, we a l s o i n t r o d u c e a new i n t o n a t i o n m o d e l t h a t c a n be a p p l i e d t o any e x i s t i n g S i n h a l a d i p h o n i c v o i c e s .