Method for compressing dictionary data

Abstract

The invention relates to pre-processing of a pronunciation dictionary for compression in a data processing device, the pronunciation dictionary comprising at least one entry, the entry comprising a sequence of character units and a sequence of phoneme units. According to one aspect of the invention the sequence of character units and the sequence of phoneme units are aligned using a statistical algorithm. The aligned sequence of character units and aligned sequence of phoneme units are interleaved by inserting each phoneme unit at a predetermined location relative to the corresponding character unit.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS [0001] This is a continuation application of application Ser. No. 10 / 292,122, filed Nov. 11, 2002, the content of which is incorporated herein by reference in its entirety.BACKGROUND OF THE INVENTION [0002] The invention relates to speaker-independent speech recognition, and more precisely to the compression of a pronunciation dictionary. [0003] Different speech recognition applications have been developed during recent years for instance for car user interfaces and mobile terminals, such as mobile phones, PDA devices and portable computers. Known methods for mobile terminals include methods for calling a particular person by saying aloud his / her name into the microphone of the mobile terminal and by setting up a call to the number according to the name said by the user. However, present speaker-dependent methods usually require that the speech recognition system is trained to recognize the pronunciation for each name. Speaker-independent spee...

AI Technical Summary

Benefits of technology

"The invention provides a more efficient method for compressing a pronunciation dictionary. The method involves pre-processing the dictionary by aligning and interleaving each entry with a statistical algorithm, such as HMM-Viterbi, to reduce the entropy of the dictionary and improve compression. The pre-processed dictionary is then used to convert speech or text into a sequence of phoneme units, which can be further processed and stored in a compressed format. The invention also includes an electronic device that performs the pre-processing and conversion steps. The technical effects of the invention include improved compression ratio, reduced memory requirement, and improved speech recognition accuracy."

Problems solved by technology

Although in many languages pronunciation of many words can be represented by rules, or even models, the pronunciation of some words can still not be correctly generated by these rules or models.

However, in many languages, the pronunciation cannot be represented by general pronunciation rules, but each word has a specific pronunciation.

In mobile phones the memory size is often limited due to reasons of cost and hardware size.

This imposes limitations also on speech recognition applications.

However, the problem with the statistical based method is that it requires a large working memory (buffer) during the decompression process.

Therefore this solution is not suitable for use in small portable electronic devices such as mobile terminals.

Although the existing compression methods are good in general, the compression of the pronunciation dictionaries is not efficient enough for portable devices.

Images