Event Categories

Event Categories#

Deeply AI system can detect various types of sound events. Each event type has its own characteristics and use cases.

Sound Level Detection#

sound_level#

• Description: General sound level detection without specific classification
• Use Case: Monitoring overall noise levels in an environment

---

Voice Events#

breathing_heavily#

• Description: Detection of heavy or labored breathing sounds
• Use Case: Health monitoring, emergency detection

crying#

• Description: Detection of crying sounds
• Use Case: Emergency situations, emotional distress monitoring

scream_female#

• Description: Detection of female screaming sounds
• Use Case: Emergency detection, security monitoring

scream_male#

• Description: Detection of male screaming sounds
• Use Case: Emergency detection, security monitoring

aggressive_yell_female#

• Description: Detection of aggressive yelling by female voices
• Use Case: Conflict detection, security monitoring

aggressive_yell_male#

• Description: Detection of aggressive yelling by male voices
• Use Case: Conflict detection, security monitoring

normal_speech_female#

• Description: Detection of normal female speech
• Use Case: General activity monitoring

normal_speech_male#

• Description: Detection of normal male speech
• Use Case: General activity monitoring

---

Emergency Keywords#

save_me#

• Description: Detection of "save me" calls for help
• Use Case: Emergency situation detection

help_me#

• Description: Detection of "help me" calls for help
• Use Case: Emergency situation detection

---

Environmental Sounds#

physical_impacts#

• Description: Detection of impact sounds (e.g., falling, collision)
• Use Case: Accident detection, security monitoring

glass_break#

• Description: Detection of glass breaking sounds
• Use Case: Break-in detection, security monitoring

---

Usage Notes#

• Each event category can be configured with different threshold values
• Thresholds determine the sensitivity of detection for each event type
• Values range from 0 to 1, where:
  • 0: Maximum sensitivity (detects even slight sounds)
  • 1: Minimum sensitivity (only detects very clear sounds)

Each threshold values are controlled by microphone. Refer to Microphone for more details.