How Vulcan Voice Works

VVsm2.gif 

Vulcan Voice is made up of two main components: the text-to-speech (TTS) and the speech recognition (SR) modules.

Text-To-Speech:

The TTS converts work instructions from the database or other source into spoken voice prompts at the speaker or headset output.

Step 1. The database provides a work instruction and passes the text to Vulcan Voice TTS

Step 2. The Vulcan Voice TTS module converts the text into human sounding phonetics

Step 3. The mobile device's audio output plays the human quality speech

 

Voice Sample Text: “Voice enabling an Enterprise is typically done within the warehouse, stockyard or manufacturing environment for pick, place, put and other inventory and maintenance related operations.” 

US English Male Voice:

Get Flash to see this player.

 

 

Speech Recognition:

The SR module takes a worker’s spoken responses from a microphone and converts them to data that can be updated in the database.

Step 1. A person speaks into the mobile device headset microphone

Step 2. The Vulcan Voice SR module converts the captured sound waves into text

Step 3. The mobile device delivers the returned text to the database

 

Speech Recognition Demonstration:
A warehouse voice picking application using Vulcan Voice

US English Female Voice:

Get Flash to see this player.

 

 

Other Voice Samples:

These samples are streams of text converted to human quality sounding voices specially compressed for use in mobile devices.

 

English UK Female

Get Flash to see this player.

 

Spanish Male

Get Flash to see this player.

 

Spanish Female

Get Flash to see this player.

 

French Canadian Male

Get Flash to see this player.

 

French Female

Get Flash to see this player.

 

Japanese Female

Get Flash to see this player.

 

Languages Available Include:

US English (ENU)
US Spanish (SPM)
Canadian French (FRC)
Brazilian Portuguese (PTB)
German (GED)
Bi-lingual German (GED / ENG support)
European French (FRF)
UK English (ENG)
Italian (ITI)
European Spanish (SPE)
Dutch (DUN)
Flemish (DUB)
European Portuguese (PTP)
Swedish (SWE)
Polish (POL)
Czech (CZE)
Russian (RUR)
Basque (BAE)
Turkish (TUT)
Australian English (ENA)
Japanese (JPJ)
Mandarin Chinese (MNC)
Cantonese (CAH)
Korean (KOK)

* To listen to samples above, click on the play arrow.

Permalink • Print

Related Entries