Answering Machine Detection

From Taridium

Revision as of 18:37, 17 June 2011 (view source) Webmaster (Talk | contribs) (→Parameters) ← Older edit		Revision as of 18:38, 17 June 2011 (view source) Webmaster (Talk | contribs) Newer edit →
Line 5:		Line 5:
	Time values are all in milliseconds unless stated otherwise.		Time values are all in milliseconds unless stated otherwise.
-	* '''initialSilence''' is the maximum silence duration before the greeting. If exceeded then MACHINE.	+	* '''initial_silence''' is the maximum silence duration before the greeting. If exceeded then MACHINE.
	* '''greeting''' is the maximum length of a greeting. If exceeded then MACHINE.		* '''greeting''' is the maximum length of a greeting. If exceeded then MACHINE.
-	* '''afterGreetingSilence''' is the silence after detecting a greeting. If exceeded then HUMAN.	+	* '''after_greeting_silence''' is the silence after detecting a greeting. If exceeded then HUMAN.
-	* '''totalAnalysisTime''' is the maximum time allowed for the algorithm to decide on a HUMAN or MACHINE.	+	* '''total_analysis_time''' is the maximum time allowed for the algorithm to decide on a HUMAN or MACHINE.
-	* '''minimumWordLength''' is the minimum duration of Voice to considered as a word.	+	* '''min_word_length''' is the minimum duration of Voice to considered as a word.
-	* '''betweenWordsSilence''' is the minimum duration of silence after a word to considere the audio what follows as a new word.	+	* '''between_words_silence''' is the minimum duration of silence after a word to considere the audio what follows as a new word.
-	* '''maximumNumberOfWords''' is the maximum number of words in the greeting. If exceeded then MACHINE.	+	* '''maximum_number_of_words''' is the maximum number of words in the greeting. If exceeded then MACHINE.
-	* '''silenceThreshold''' is the silence threshold.	+	* '''silence_threshold''' is the silence threshold.
	== Example AMD Configuration ==		== Example AMD Configuration ==

---

Revision as of 18:38, 17 June 2011

This application attempts to detect answering machines at the beginning of outbound calls. It is used in a variety of ipbx application to detect answering machines. AMD settings can be configured in the Administrator Panel under Configuration → Manual Editor → Answering Machine Detection

Parameters

Time values are all in milliseconds unless stated otherwise.

• initial_silence is the maximum silence duration before the greeting. If exceeded then MACHINE.
• greeting is the maximum length of a greeting. If exceeded then MACHINE.
• after_greeting_silence is the silence after detecting a greeting. If exceeded then HUMAN.
• total_analysis_time is the maximum time allowed for the algorithm to decide on a HUMAN or MACHINE.
• min_word_length is the minimum duration of Voice to considered as a word.
• between_words_silence is the minimum duration of silence after a word to considere the audio what follows as a new word.
• maximum_number_of_words is the maximum number of words in the greeting. If exceeded then MACHINE.
• silence_threshold is the silence threshold.

Example AMD Configuration

 [AMD] 
 initial_silence = 2500 
 greeting = 1500 
 after_greeting_silence = 300 
 total_analysis_time = 4000 
 min_word_length = 120 
 between_words_silence = 50 
 maximum_number_of_words = 5 
 silence_threshold = 256