Semi-automatic sound file labeling method, system and equipment

The invention provides a semi-automatic sound file labeling method, system and equipment. The method comprises the following steps: acquiring a sound file signal to be processed; preprocessing the to-be-processed sound gear signal to obtain a preprocessed sound gear signal; utilizing a plurality of...

Full description

Saved in:
Bibliographic Details
Main Authors JIAN RENXIAN, LIN CHANGZHOU, XU YALING
Format Patent
LanguageChinese
English
Published 31.12.2021
Subjects
ACOUSTICS
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
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:The invention provides a semi-automatic sound file labeling method, system and equipment. The method comprises the following steps: acquiring a sound file signal to be processed; preprocessing the to-be-processed sound gear signal to obtain a preprocessed sound gear signal; utilizing a plurality of voice recognizers to respectively convert the preprocessed voice file signals into text information; reprocessing the character information obtained by each voice identifier to obtain reprocessed character information; and receiving manual annotation information input for the reprocessing character information, and completing annotation of the sound file signal to be processed. According to the method, the voice recognition result can be provided for labeling personnel for reference during manual labeling. In this way, when the voice signals are marked, marking personnel do not need to mark the voice signals after recognizing the voice signals, but can directly mark the voice signals according to the character sign
Bibliography:Application Number: CN202111056108