Speech Recognition

  • HOME > 
  • Speech Recognition > 
  • Selvy STT-Server

Selvy STT-Server

stt_intergrated_service
SELVAS AI has exclusively developed core elements in the overall speech recognition (STT server) process, from speech detection, feature extraction and sound effect modeling to navigation and post-processing. We have secured a high recognition of the Korean language by reflecting the language’s characteristics and vocalization habits, not to mention the support of high-quality consultancy through our R&D and commercialization performance over the last 10 years.
  • Expands/modifies the scope of words recognized with features such as isolated command, large-scale POI, variant words and connective words
  • Features various recognition engines applicable to H/W specifications and application scenarios
  • Allows the speaker to repeat utterances and prevents incorrect recognition by assessing the user ¡s vocalization history
  • Ensures recognition performance in diverse, noisy environments by adopting multiple sound effect modeling tools and multi-phase recognition methods
  • Enables an efficient and shortened development period by configuring a concise API
  • Requires only a small amount of system resources to run
  • Supports a convenient upgrade feature by modulating the recognition engine library
  • Strong noise-proof recognition performance is achieved by applying multi-channel noise reduction technology
  • Solution proven through obtaining the Good Software (GS) certification

Selvy STT-VLog

stt service
With the speech-to-text function primarily based on continuous speech recognition technology (stt service), VLog provides an integrated service ranging from statistics and inquiries through voice search.

This solution (stt service) enables users to quickly and efficiently make documents using continuous speech, which can be recorded during company meetings and telephone conversations with banks or insurance companies. With an information retrieval function, as well as extraction, statistics and data classification functions, it can be applied in various scenarios, including call-centers, where speech data is required to be stored on mass, in order that it can be utilized and managed. 

VLog provides a fast and high-qualitystt service by directly interlinking with a speech storing server and through the best continuous speech recognition engine which possesses a large amount of vocabulary.
Major Application Examples  
Consulting and recording solution providers 
VLog is applied to the QA's sales inspection to detect changes to
contract agreements and changes to insurance policies.
Text parsing companies
The best choice for companies who provide high volumes of data analysis in text and now want to utilize this data verbally in telephone and data networks

Applicable markets

stt solution

Features and benefits of the solution

stt_feature

Possesses the core technology
for speech recognition,
optimized for recording


 Possesses the core technology for speech recognition engines

 Provides cutting-edge technology for
continuous speech recognition
and keyword speech recognition

 Possesses the nation's largest number of
specialists in speech recognition technology,
working on improving speech recognition performance

 Available for systematic development with
other developing companies, along with the source technology for speech recognition

 Available for structural changes and optimized to
perform product-specific tasks at engine level
stt-engine

Combines the strengths of continuous
speech engines and keyword engines 


 The continuous speech recognizer
can extract information by using contextual
information rather than the keywords.

 Provides continuous speech of
a high volume of vocabulary, in real-time,
and at a stable recognition rate

 Provides reliable speech matching by
recognizing keywords according to the
recognition reliability of the continuous
speech recognition results
stt_automation

Automation toolkit for quickly
improving the performance
(faster build-up time) 


 Semi-automatic sound/language
modeling training toolkit