BlueCore5 Multimedia Supports Text-to-Speech and Speech Recognition for Bluetooth Headset and Car Kit - CSR

Posted in Audio, Automotive, Bluetooth, Entertainment, Mobile Devices
On Monday, April 28, 2008

CSR’s BlueCore5-Multimedia platform now supports Speech Synthesis /
Text-to-Speech (TTS)
and Speech Recognition (SR) functionality. By
combining Text-to-Speech and Speech Recognition technologies, CSR provides users
with ultimate control when communicating via either a Bluetooth headset or
embedded car kit. When a call is received on the user’s mobile phone, the
speech synthesis engine announces the name or number of the caller
, allowing
the user to decide whether or not to accept the call, and use Speech Recognition
to answer the call without the need to press a button.

Text-to-Speech and Speech Recognition

CSR’s BlueCore5 Multimedia with Text-to-Speech and Speech Recognition

Anthony Murray,  CSR, said:

CSR’s BlueCore5-Multimedia platform is the only Bluetooth device in the
market that provides a speech controlled user interface for the Bluetooth
accessory market. Thanks to CSR’s powerful integrated DSP on-chip, eXtension
Partners such as NowSpeak and Rubidium can provide true hands-free experience
to our customers on a single-chip, reducing the total cost of eBoM for
customers…

Speech synthesis (Text-to-Speech) can be used as a connection and pairing
status guide and can inform the user of the title of a music track played over
Bluetooth. Furthermore, Speech Recognition allows users to easily and safely
control a vast array of functions through voice commands, including call
acceptance and rejection, voice dialling, and music control and selection.
Text-to-Speech and Speech Recognition together provide users of a CSR
BlueCore5-Multimedia based product with the ultimate hands free experience.

Text-to-Speech and Speech Recognition  is developed through CSR’s eXtension Partner Programme with NowSpeak and Rubidium Ltd. NowSpeak offers the
complete handsfree interface for CSR BlueCore devices with its next generation
text-to-speech and speech recognition products. Its text-to-speech technology
automatically synthesizes speech from text in real time and has been
specifically optimized to speak people’s names, phone numbers and device status
phrases with a natural voice. With support for all major languages and a small
memory footprint it is possible to include multiple languages in a Bluetooth
device. Its speaker independent speech recognition requires no user training,
supports multiple vocabularies and can be used to recognise words, digits or
whole phrases. NowSpeak’s speech recognition is designed to work in real world
situations with background noise reduction and rejection of unwanted sounds.
NowSpeak text-to-speech and speech recognition solutions can be integrated
together or used independently.

Rubidium’s Text-to-Speech and Speech Recognition offering, is available on
the CSR BlueCore5-Multimedia platform. Rubidium’s Text-to-Speech uses
concatenate Text-to-Speech based on real human speech to produce pure and natural sound,
while keeping use of computational resources exceptionally low. It supports
diverse languages, and was designed to offer rapid and flexible addition of
virtually any language and voice. Rubidium’s core Speech Recognition technology
derives from its proprietary Rubidium Dialog Engine series, featuring speaker
independent recognition and supporting keyword spotting and noise robustness. Optimised to support essentially any language and accent, it uses artificial
intelligence elements to cope with natural language, dynamic vocabularly and
multi-layer dialogues.

CSR’s BlueCore5-Multimedia has been specifically designed to enable best in
class audio for applications including high-end stereo and mono headsets. Its
powerful 64 MIPS DSP allows customers to add audio or voice enhancement software
available through CSR’s eXtension Partner Program to further boost the
performance and functionality of their end designs.

More info: CSR


Possible Related Entries:
[Embedded System roll-b]
Caution:
Non-English page is generated by an automatic translation software which can rise inaccurate translation.
Consider to view the original English version via link at the bottom of this page.