We’re currently using these amd.conf settings and was wondering if anyone had any more effective settings or knew of a way todo the following
- Play your pompt and detect voice activity.
- If the voice activity happens between say 4 and 5 seconds you know it’s
either a) noisy env or b) an answering machine.
- Once we’ve determined it’s answering machine wait for no voice activity and play the voicemail prompt.
; Answering Machine Detection Configuration
initial_silence = 3500 ; Maximum silence duration before the greeting.
; If exceeded then MACHINE.
greeting = 1500 ; Maximum length of a greeting. If exceeded then MACHINE.
after_greeting_silence = 800 ; Silence after detecting a greeting.
; If exceeded then HUMAN
total_analysis_time = 5000 ; Maximum time allowed for the algorithm to decide
; on a HUMAN or MACHINE
min_word_length = 120 ; Minimum duration of Voice to considered as a word
between_words_silence = 50 ; Minimum duration of silence after a word to consider
; the audio what follows as a new word
maximum_number_of_words = 5 ; Maximum number of words in the greeting.
; If exceeded then MACHINE
silence_threshold = 256
Thanks for your help.