Microchip Technology AC162060 Data Sheet
© 2005 Microchip Technology Inc.
DS30177T-page 15
Software
dsPIC30F Speech Recognition Library
The dsPIC30F Speech Recognition Library provides
voice control of embedded applications that require an
alternative user interface. With a vocabulary of up to
100 words, the Speech Recognition Library allows
users to control their applications vocally. The Speech
Recognition Library is an ideal front-end for hands-free
products, such as modern appliances, security panels
and cell phones. The Speech Recognition Library has
very modest memory and processing requirements.
voice control of embedded applications that require an
alternative user interface. With a vocabulary of up to
100 words, the Speech Recognition Library allows
users to control their applications vocally. The Speech
Recognition Library is an ideal front-end for hands-free
products, such as modern appliances, security panels
and cell phones. The Speech Recognition Library has
very modest memory and processing requirements.
Features
• Speaker-independent recognition of isolated words
• Hidden Markov Model-based recognition system
• Recognition time < 500 msec
• Master library of 100 common words
• Windows
®
operating system-based utility allows you
to create a custom library from the master library
• Additional words can be added to the master library
(fee-based)
• No speaker training is required
• US English language support
• Data tables can be stored in external memory
• Optional keyword activation and silence
detection
• Optional system self-test using a predefined
keyword
• Flexible API
• Full compliance with Microchip MPLAB
®
C30
language tools
• “dsPIC30F Speech Recognition Library User’s
Guide”
The Speech Recognition Library provides isolated,
speaker-independent word recognition of US English. It
allows the user to control an application through a set
of fixed, voice commands.
speaker-independent word recognition of US English. It
allows the user to control an application through a set
of fixed, voice commands.
The library has already been pretrained by a
demographic cross-section of male and female US
English speakers. Conveniently, no training is required
for end users of the product.
demographic cross-section of male and female US
English speakers. Conveniently, no training is required
for end users of the product.
The library samples speech data from a voice codec
connected to the dsPIC30F device’s Data Converter
Interface. The data is processed a frame at a time, and
when a word ending is detected, the received word is
identified using Hidden Markov Model processing. After
the library identifies the word, your application may
then take some predefined action.
connected to the dsPIC30F device’s Data Converter
Interface. The data is processed a frame at a time, and
when a word ending is detected, the received word is
identified using Hidden Markov Model processing. After
the library identifies the word, your application may
then take some predefined action.
The Speech Recognition algorithm is written in
Assembly language to optimize performance and
minimize RAM usage. A well-defined API makes it
easy to integrate the Speech Recognition Library with
your application. Library functions let your application
easily disable and enable speech recognition. The
library lets your other system processing operations
take place without disrupting speech recognition.
Assembly language to optimize performance and
minimize RAM usage. A well-defined API makes it
easy to integrate the Speech Recognition Library with
your application. Library functions let your application
easily disable and enable speech recognition. The
library lets your other system processing operations
take place without disrupting speech recognition.
Ordering Information:
SW300010-EVAL dsPIC30F Speech Recognition Library Software License (Evaluation Copy)
SW300010
dsPIC30F Speech Recognition Library Software License (Up to 5K units)
SW300011
dsPIC30F Speech Recognition Library Software License (5K to 25K units)
SW300012
dsPIC30F Speech Recognition Library Software License (25K to 100K units)
AC300031
Accessory Kit (includes: microphone, headset and 6.144 MHz clock oscillator)
DS51465
“dsPIC30F Speech Recognition Library Product Overview” (Available at: www.microchip.com)