METHOD AND APPARATUS FOR CONDITIONING NEURAL NETWORKS

Broadly speaking, the present techniques provide methods for conditioning a neural network, which not only improve the generalizable performance of conditional neural networks, but also reduce model size and latency significantly. The resulting conditioned neural network is suitable for on-device de...

Full description

Saved in:
Bibliographic Details
Main Authors MEHROTRA, Abhinav, RAMOS, Alberto Gil C. P, BHATTACHARYA, Sourav
Format Patent
LanguageEnglish
French
German
Published 14.12.2022
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:Broadly speaking, the present techniques provide methods for conditioning a neural network, which not only improve the generalizable performance of conditional neural networks, but also reduce model size and latency significantly. The resulting conditioned neural network is suitable for on-device deployment due to having a significantly lower model size, lower dynamic memory requirement, and lower latency.
Bibliography:Application Number: EP20220172819