SBIR-STTR Award

Automatic Spoken Language Recognition for Machine Foreign Language Translation (MFLT)
Award last edited on: 5/9/2014

Sponsored Program
SBIR
Awarding Agency
DOD : Army
Total Award Amount
$642,615
Award Phase
2
Solicitation Topic Code
A12-031
Principal Investigator
Kornel Laskowski

Company Information

Voci Technologies Inc (AKA: Silicon Vox Corporation)

6301 Forbes Avenue Suite 120
Pittsburgh, PA 15217
   (412) 621-9310
   info@vocitec.com
   www.vocitec.com
Location: Single
Congr. District: 18
County: Allegheny

Phase I

Contract Number: ----------
Start Date: ----    Completed: ----
Phase I year
2012
Phase I Amount
$150,000
Voci Technologies Incorporated (Voci™) is partnering with Bhiksha Raj, a Voci advisor and Professor at Carnegie Mellon University, to prototype an Automated Spoken Language Recognition System (ASLRS) specifically designed to enhance the utility of Speech to Speech Machine Foreign Language Translation (MFLT) systems for the warfighter. The proposed ASLRS will be developed by tailoring Voci’s existing language identification technologies to fulfill the requirements of an efficient MFLT preprocessor. To provide best in class accuracy, a combination of techniques will be used including acoustic UBM-GMM (Universal-Background-Model/Gaussian-Mixture-Model), and PPRLM-SVM (Parallel-Phonetic-Recognition-Language-Model/Support-Vector-Machine). To meet the ASLRS real-time requirements a groundbreaking, patent pending, multi-language phonetic dictionary capable of doing phonetic recognition in all 6 target languages in a single pass will be utilized. An open-set based solution will be provided so that the ASLRS will recognize when an out of domain language is spoken. To ensure that the resulting ASLRS is generally applicable, it will be architected to be an open system that is easily integratable with existing MFLT solutions. To ensure that the system provides reliable results, even in noisy environment, the system will incorporate noise robust features. Finally, to address the shortcomings of existing solutions in real-world field conditions, the Voci Team will integrate an online incremental learning capability into the ASLRS so that it can adapt to different accents and noise conditions that exist during field use. At the end of Phase I the Team will demonstrate the prototype ASLR system. We believe the final implementation will yield a revolutionary new ASLR capability.

Keywords:
(1) Automated Spoken Language Recognition, (2) Human Language Technology, (3) Language Identification (Lid), (4) Gender Identification, (5) Speaker Identification (Sid), (6) W

Phase II

Contract Number: ----------
Start Date: ----    Completed: ----
Phase II year
2013
Phase II Amount
$492,615
Voci Technologies Incorporated (Voci?) is partnering with Carnegie Mellon University (CMU) to develop and demonstrate a prototype Automated Spoken Language Recognition System (ASLRS). The ASLRS is specifically designed to enhance the usability of Speech to Speech (S2S) Machine Foreign Language Translation (MFLT) systems for the warfighter. The proposed ASLRS will leverage the Team?s existing language identification capabilities, experience, and expertise to fulfill the requirements of an efficient MFLT preprocessor. Best-in-class accuracy will be achieved using a combination of techniques and fusing the results. To meet the real-time requirements, a ground-breaking, patent-pending, multi-language phonetic dictionary capable of doing phonetic recognition in all 6 target languages in a single pass will be utilized. An open-set solution will be provided so that the ASLRS recognizes when an out-of-domain language is spoken. To ensure that the resulting ASLRS is generally applicable, it will be architected to be an open system, ensuring that it is inter-operable with existing MFLT solutions and that it supports the addition of new languages. To ensure that the system provides reliable results, even in noisy environment, the system will incorporate noise robust features. Finally, to address the shortcomings of existing solutions in real-world field conditions, the Team will integrate a learning capability into the ASLRS so that it can adapt to different accents and noise conditions that exist during field use. At the end of Phase II, the Team will demonstrate the prototype ASLRS on a mobile device (e.g., Android smartphone). We believe the final implementation will revolutionize S2S MFLT use in the field.

Keywords:
(1) Automated Spoken Language Recognition, (2) Human Language Technology, (3) Language Identification (Lid), (4) Gender Identification, (5) Speaker Identification (Sid), (6) W