This paper presents a method for, a n d performance of, p h o n e m e s e g m e n t a t i o n b y a n e x p e r t s y s t e m u t i l i z i n g spectrogram reading strategy a n d knowledge. T h e e x p e r t system detects phonemes i n a spectrogram a n d determines their b o u n d a r i e s as well as their c o a r s e categories. T o simulate a human expert spectrogram reading process, the system performs assumption-based inference with certainty factors, a n d top-down acoustic f e a t u r e extraction u n d e r phonetic c o n t e x t hypotheses. T h e system, i n t o w h i c h J a p a n e s e c o n s o n a n t s e g m e n t a t i o n k n o w l e d g e is incorporated, is able to detect ahout 90% of the phonemes correctly. I n particular, t h e phoneme boundaries detected b y the system a r e as accurate as those detected b y h u m a n experts. T h e result is that the phonemes obtained b y t h e expert system can h e identified using a stochastic phoneme recognition method.

No abstract

This p a p e r d e s c r i b e s a p h o n e m e recognition e x p e r t system combining spectrogram r e a d i n g k n o w l e d g e a n d neural networks. Consonant recognition is performed i n t h r e e stages: 1) C o n s o n a n t s e g m e n t a t i o n b a s e d on spectrogram reading knowledge. 2) Consonant identification based on neural networks. 3) Final consonant determination combining the results of the consonant segmentation a n d identification stages. T h e m e c h a n i s m s f o r c o m b i n i n g consonant segmentation a n d identification were studied to en hence their respective advantages. Consonant recognition experiments a r e carried out, a n d show t h a t t h e organic combination of segmentation a n d TDNN improves not only phoneme identification performance b u t also segmentation accuracy. Furthermore, it effectively r e d u c e s i n s e r t i o n errors. Vowel recognition uses phoneme-spotting n e u r a l networks for vowel detection a n d s p e c t r o g r a m r e a d i n g knowledge for verifying its identity a n d t h e boundaries. The effectiveness of this a p p r o a c h is shown through a vowel detection experiment.

No abstract

No abstract