Browse Prior Art Database

Personalized Voice Mail

IP.com Disclosure Number: IPCOM000015971D
Original Publication Date: 2002-May-19
Included in the Prior Art Database: 2003-Jun-21
Document File: 2 page(s) / 42K

Publishing Venue

IBM

Abstract

Business Need In future an increase of use of e-mails with acoustical (spoken) messages is expected. On one hand due to the use of dictation systems (e.g. IBM Via Voice ®) speech is revalued as an input to information technology systems. On the other hand an increasing number of applications allow the use of acoustical attachments (e.g. *.wav). Furthermore classical e-mail and SMS (short message services) is developing towards a mass communications system. It would be more practicable for many of the end users, if the output of e-mails and SMS would be in spoken instead of written form. Present Situation

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 1 of 2

Personalized Voice Mail

Business Need

    In future an increase of use of e-mails with acoustical (spoken) messages is expected. On one hand due to the use of dictation systems (e.g. IBM Via Voice ®) speech is revalued as an input to information technology systems. On the other hand an increasing number of applications allow the use of acoustical attachments (e.g. *.wav).

    Furthermore classical e-mail and SMS (short message services) is developing towards a mass communications system. It would be more practicable for many of the end users, if the output of e-mails and SMS would be in spoken instead of written form.

Present Situation

    Presently there are solutions under development (or even in use) which allow hearing the e-mails instead of reading it. These systems transpose messages received in e-mail format to acoustical information. This allows receiving of e-mails during other activities (e.g. while being on the road). These informations are generated using a "standard voice" by the present systems.

    There is a strong demand that the e-mails would be reproduced using the voice of the sender.

    This is possible on the one hand by transmission of acoustical recorded information (*.wav), following the principle of a normal voice box or answering machine. This approach uses an enormous bandwidth. Also the storing of the audio files needs a not neclectable amount of place on the hard disks both on sender and receiver side.

Proposed Solution The underlying idea is the transmission of the "pure" information and the electronically generation of the sender's voice during message reproduction. This follows the reverse principle of speech input devices, which transpose voice input into information (preferably independent of the speaker). For the personalized voice output of an information it is necessary that a speech profile of the sender is available on receiver's si...