
Philo-S
Deep learning-based voice recognition and quality enhancement solution
It is a voice recognition and speech separation & analysis solution that learns voice data through a deep learning-based acoustic model, enhances voice recognition, speech classification capabilities as well as quality through RNN-based speech vector generation

Real-time voice recognition API service

Speech separation /analysis & noise elimination through voice filtering technology

Speech synthesis though text information
Features
Speech with Noise
Noise elimination by applying voice filtering


Speech recognition & separation + Quality enhancement

Configuration


Use
AI Speaker

-
Improved Speech recognition ratio
-
STT for AI speaker’s NPL process
-
Collaboration with leading AI speaker manufacturers



Realtime call transcripts to text
-
Recognizes the voice of each speaker separately and records the call as a text document
-
Possible integration with video call platforms
Speech Synthesis

-
Reads text information in a selected voice
-
AI professional announcer’s voice function

Automated Subtitle Generator

-
Generates subtitles automatically by extracting audios directly from movies or audio files
-
Automated lyrics generation

Telemedicine
-
Q&A between doctors & patients
-
Realtime diagnosis
-
Possible integration with video call platforms



Online Classes

-
Recognizes instructor’s voice and generates handwritten notes automatically
-
Natural communication & feedback environment (Q&A)
Video Conferencing

-
Enhancement of voice quality by eliminating noise for each speaker
-
Automatically generates meeting minutes by each speaker through feature extraction and separation
-
Possible integration with video conferencing platform




Case study
Online class service provider
AI solution for advanced voice quality of multi-user online lecture platform
