Variable Speed Speech Synthesis
Navy SBIR FY2008.2


Sol No.: Navy SBIR FY2008.2
Topic No.: N08-149
Topic Title: Variable Speed Speech Synthesis
Proposal No.: N082-149-0858
Firm: Li Creative Technologies
30 A Vreeland Road, Suite 130
Florham Park, New Jersey 07932-1924
Contact: Qi Li
Phone: (973) 822-0048
Web Site: www.licreativetech.com
Abstract: We propose a completely trainable speech synthesis solution that is capable of synthesizing variable speed speech from different speakers under various speaking status. Specifically, our proposed system consists of a speaking status synthesis module, a speaker (accent) morphing module and a text-to-speech synthesis module. The novelty and uniqueness of our proposed approach are as follows: First, it decouples speaking status and speaker voice characteristics, and model them separately; second, it comprises two completely trainable modules. This allows the system to synthesize a variety of speech, e.g. fast speech under highly stressful condition.
Benefits: The technology developed under this SBIR can be transitioned into a commercial product for use by Homeland Security/Defense as well as other defense research and development entities, for example, in Close Air Support training. This technology will have commercial applications for any organization that utilizes speech synthesis technology to support development of tools to support accessibility (e.g., screen readers for people with visual impairment) and telephone-based systems (e.g., automated call centers). The technology would also be useful to government, industry and academic organizations that develop training systems that require the user to interact with a computer to train team skills.

Return