20240021206. DIARIZATION USING ACOUSTIC LABELING simplified abstract (VERINT SYSTEMS INC.)
Contents
DIARIZATION USING ACOUSTIC LABELING
Organization Name
Inventor(s)
Ran Achituv of Hod Hasharon (IL)
Jeremie Dreyfuss of Tel Aviv (IL)
DIARIZATION USING ACOUSTIC LABELING - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240021206 titled 'DIARIZATION USING ACOUSTIC LABELING
Simplified Explanation
The abstract describes a system and method for diarization of audio files using an acoustic voiceprint model. The system analyzes multiple audio files to create an acoustic voiceprint model associated with a specific speaker. Metadata from an audio file is used to select the appropriate acoustic voiceprint model. The selected model is then applied in a diarization process to identify audio data from the identified speaker.
- The system uses an acoustic voiceprint model to perform diarization of audio files.
- Multiple audio files are analyzed to create the acoustic voiceprint model.
- Metadata from an audio file is used to select the appropriate acoustic voiceprint model.
- The selected model is applied in a diarization process to identify audio data from the identified speaker.
Potential applications of this technology:
- Speech recognition systems can benefit from accurate diarization of audio files.
- Transcription services can improve their efficiency by automatically identifying speakers in audio recordings.
- Law enforcement agencies can use this technology for voice identification and analysis in criminal investigations.
- Call center operations can enhance their customer service by automatically identifying speakers during phone conversations.
Problems solved by this technology:
- Manual identification of speakers in audio files can be time-consuming and prone to errors. This technology automates the process, saving time and improving accuracy.
- Traditional diarization methods may not be effective in cases where the speaker's voice characteristics change over time. The use of an acoustic voiceprint model helps overcome this challenge.
Benefits of this technology:
- Improved efficiency and accuracy in diarization of audio files.
- Time-saving for transcription services and other applications that require speaker identification.
- Enhanced voice identification capabilities for law enforcement agencies.
- Improved customer service in call center operations through automated speaker identification.
Original Abstract Submitted
systems and method of diarization of audio files use an acoustic voiceprint model. a plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. metadata associate with an audio file is used to select an acoustic voiceprint model. the selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.