A Surficial Pronunciation Model

A Surficial Pronunciation Model (1998)

by Eric Sven Ristad , Peter N. Yianilos

Venue:	In: Proc. of the ESCA Workshop ‘Modeling Pronunciation Variation for Automatic Speech Recognition’ (see [87
Citations:	3 - 0 self

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	A Surficial Pronunciation Model	user correction - Legacy Corrections
AUTHOR NAME	Eric Sven Ristad	SVM HeaderParse 0.1
AUTHOR AFFIL	1	SVM HeaderParse 0.2
AUTHOR NAME	Peter N. Yianilos	SVM HeaderParse 0.1
AUTHOR AFFIL	; 2; 1; Mnemonic Technology, Inc., Princeton; 2; NEC Research Institute, Princeton	SVM HeaderParse 0.2
AUTHOR ADDR	; NJ, USA; NJ, USA	SVM HeaderParse 0.1
ABSTRACT	We argue for a surficial pronunciation model: a model without underlying forms. The surficial model outperforms a traditional generative model by a significant margin on conversational speech (Switchboard) as well as on read speech (TIMIT). Our results suggest that the true mapping from underlying forms to surface forms is too complex to be accurately modeled using current techniques, and that we would be best served to model the surface forms directly.	user correction - Legacy Corrections
YEAR	1998	INFERENCE
VENUE	In: Proc. of the ESCA Workshop ‘Modeling Pronunciation Variation for Automatic Speech Recognition’ (see [87	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	117--120	INFERENCE
CITATIONS	11 found	ParsCit 1.0