Latest News:
more ▼
|
-
"Efficient Ensemble of Deep Neural Networks for Multimodal Punctuation Restoration and the Spontaneous Informal Speech Dataset," Electronics Vol. 14, No. 5, 973, Feb. 2025
-
Tech. Report RTI-20240822-01: "MLP, XGBoost, KAN, TDNN, and LSTM-GRU Hybrid RNN with Attention for SPX and NDX European Call Option Pricing"
-
Recognition Technologies, Inc. June 13, 2024 Westchester County’s Tech Accelerator Demo Day
-
Tech. Report RTI-20240524-01: "Carnatic Raga Identification System using Rigorous Time-Delay Neural Network"
-
IEEE IMCOM (2024): Efficient Ensemble for Multimodal Punctuation Restoration using Time-Delay Neural Network
|
|
|
See Demonstration Videos ▼
|
RecoMadeEasy®Products
A single comprehensive software engine for enabling Speech, Speaker, Face, Object, Emotion Recognition, Translation, Access Controls, and much more, using a unified set of APIs designed for Integrators and Software Developers -- works standalone (Android and Linux) and in client/server mode
|
|
|
-
AudioVisual Recognition
(Embedded)
(Server Based)
(Combination of Speaker, Speech, Face Recognition, and Object Detection and Recognition with a single interface)
-
Large-Vocabulary Speech Recognition
(Embedded)
(Server Based)
Initially available for English, Spanish, Mandarin, Arabic, and German, is now available for 100+ languages
Also includes multilinguagl support and code-switching
(Customizable domain full transcription ~ 300,000+ word vocabulary)
-
Speaker Recognition
(Embedded)
(Server Based)
(Language- and Text-Independent, aka: Speaker Biometrics, Voice Biometrics, or SIV)
Recipient: Frost & Sullivan Award 2011
-
Face Recognition
(Embedded)
(Server Based)
(Face detection and recognition)
-
Object Recognition
(Embedded)
(Server Based)
(Object detection and recognition)
RecoMadeEasy® (Reco Made Easy)
Embedded Object Recognition
Platform:
RecoMadeEasy® Embedded Object Recognition is an embedded image and video recognition engine that offers comprehensive object detection and object recognition. The engine has a small memory footprint and is designed to run natively on devices that seek high recognition accuracy in the presence of service interruption or when full, uninterrupted and secure access to a cloud server is not guaranteed.
The RecoMadeEasy® Object Recognition engine
has been developed in our research labs in New York. When
presented with a video stream or set of images, the engine via
the API returns its results in the form of XML
or JSON. The results include the timestamp where an object
has been detected and Label of the object in that
image. It is also capable of learning new object when
presented with a Tag at enrollment.
The RecoMadeEasy® Object Reocgnition engine is also available as a server-side and a standalone product. It provides object
detection, object identification, and
facial verification from still images and video streams. It
supports all standard image and video formats such as png, jpeg,
gif, mp2, mp4, .mov, etc.
Supported Operating Systems
The RecoMadeEasy® Embedded Object
Recognigtion engine is available for the following operating
systems. The C++ SDK, command-line interface, and web
services may be used in any of the following systems:
Embedded Operating Systems:
- Android (aarch64 -- armv8a)(Latest)
- Ubuntu 22.04 Mate Linux (aarch64)(Latest)
|
|