E-Speech Name Pronunciation Products


	Name Pronunciation

	Home
	Products
	Speech Synthesis
	Name Pronunciation
	Text Preprocessing
	Custom Products
	Demos
	Customers
	Consulting
	News
	About E-Speech
	Contact Us

E-Speech offers letter-to-phoneme software that provides the most accurate name pronunciation available today for the names of people, businesses, and places in the United States. E-Speech software is also excellent at pronouncing English words, so that it can be used for general text as well as for name-oriented applications.

We have released version 2 of the E-Speech name pronunciation software, containing many improvements over the original software, especially for business and geographical terms. Our software includes verified pronuniciations for many thousands of names, and in addition, our software provides multiple pronunciations for many names that have more than one possible pronunciation. For example, a name like "Migliore" may be pronounced as "mig lee or", "mig lee or ee", "mig lee or ay", "mil yore", "mil yore ee", or "mil yore ay." This feature is important for speech recognition applications, since they must be able to link all the pronunciations to the same name. It can be used with speech recognition and with text-to-speech, and it supports popular phonetic alphabets. E-Speech offers the most accurate pronunciation software available today for the names of people, places, and businesses in the United States. The software runs on Win95/98/NT/2000/XP and various Unix systems, including Linux, and is easy to integrate with applications.

Our software will give you unparalleled name pronunciation accuracy for any application:
      • speech recognition
      • the front-end for any speech synthesizer
      • coaching agents in outbound call centers on how to pronounce names of people or places
      • brand-naming or word searching: it can identify what words or names sound like other words or names

The software translates input in English orthography into a phonological representation, in ARPAbet, CPA, SAMPA, HARK, or the E-Speech phonetic alphabet, indicating phonemes, word-stress, syllable boundaries, word and phrase boundaries, and optionally, intonation and phrase-stress.

For example,

Input	Output
Gerhardt Lachapelle	gey'r$haart laa$shax$peh'*l
Daphne Murtagh	dae'f$niy mer'*$tao
PETsMART	peh'*t$smaart
Daimler-Chrysler	day'm$ler kray'*$sler
Bionx Corporation	bay$aa'*$nihks kaor$per$ey'$shaxn
Cafe de Paris	kae$fey' duh pae$riy'*
Tiburon Grille	tih'$ber$aan grih'*l
Cabernet Sauvignon	kae$ber$ney' sow$vihn$yow'*n
Azalea Court	ax$zey'l$yax kao'*rt
Bryn Mawr	brih'n maa'*r
Skaneateles	skae$niy$ae'*$tax$liyz
Lake Okeechobee	ley'k ow$kax$chow'*$biy

The software provides alternate pronunciations for names and words with multiple pronunciations, such as Weinstein, bass, and read.

Our letter-to-phoneme software can be used real-time during speech recognition/synthesis transaction processing or off-line to build pronunciation dictionaries that can be incorporated into your ASR or synthesis software. The software is available as part of the E-Speech synthesizer or as a standalone system. The standalone version is available as a command-line executable or as a library/DLL containing C-callable functions. Our software is available for Win32 and a variety of Unix platforms. We welcome customization: we are happy to tailor our software to your specific needs.