IntroductionAPPLIED TECHNOLOGIES

  • home
  • APPLIED TECHNOLOGIES
  • LARGE VOCABULARY CONVERSATIONAL SPEECH RECOGNITION

LARGE VOCABULARY CONVERSATIONAL SPEECH RECOGNITION (LVCSR)

This technology recognizes the speaker's voice using an acoustic model and language model. LVCSR is comprised of a large vocabulary of around 200,000 words. Configured as a distributed voice recognition system of a server – client format, LVCSR is made up of a pre-processor, which is for signal processing and characteristic extraction, search module, which uses an acoustic model, phonetic dictionary and language model, and post-processing module.
Key algorithm
This language model using optimized language processing units to consider acoustic model reflecting phonemic changes, pronunciation generation rule algorithm, dictionary size and out-of-vocabulary is a technology to change voice to text.
Pre-processor
Removes noise, improves sound quality
Extracts information from voice section
Extracts voice characteristic parameters
Acoustic model
Models characteristics of voice signal that changes over time
HMM and NN used
Phonetic dictionary
Automatically generates pronunciation of Korean words
Supports multiple pronunciations
Language model
A grammatically correct sentence obtains a higher score as grammar between words is considered and weight is
  placed on recognition candidates.
Language model is selected considering the number of target vocabularies recognized, such as FSN and
  n-gram, as well as speed of recognition and recognition performance.
WFST (weighted finite-state transducer)-based decoder
High-speed/ efficient memory management
LM (language model) based on colloquial style n-gram specialized to smart convergence/ vehicular environment
Post-processor
Module to improve recognition performance or calculate reliability of recognition result by processing such
  result
Technological service
Application
*Click icon to read detailed descriptions.