When an outbound call is made, Voicent auto dialer software has to detect whether the call is answered by a live human or an answering machine (or voicemail). This process is called ‘call progress detection’ and it is based on analyzing the incoming audio. Traditionally (when computers are slow) the detection is implemented in hardware, and due to the limitations of hardware implementation, the accuracy is not that great. Voicent’s detection algorithm is based on intelligently analyzing the incoming audio and apply the best fit patterns based on statistics. We have spent a lot of research time to improve the detection algorithm and our accuracy is second to none in the industry.
However, no system today can achieve 100% accuracy (this include humans in a noisy environment). This KB artile offers more detailed discussions on the issue and some key factors that may affect the detection accuracy.
When a phone call is answered, an autodialer system needs to play a message a) immediately for live human pickup, and b) until a beep sound is detected for answering machine or voice mail system. Based on the answering party, the system then decides whether to play or wait. Unfortunately, there is no tone or signal over the phone line that indicates the pickup situation. Hence the system has to analyze the audio stream over the phone line in order to make a decision.
What can complicate the detection process
Strong background noise can be hard to filter out, especially it is from a human voice. A loud TV in the background, a second person talking to other person, etc, can mislead the system to make an answering machine prediction for human pickup.
On the other hand, a very weak answering machine volume can be diagnosed as background noise. So the system might think it is a live human pickup and play the message too early.
Another factor is that people answer the phone differently. There are really no fixed patterns or even regular patterns to follow. People from different countries, from different ethnic groups answer the phone differently. The system is tuned for north american population where people usually answer with a short “hello”.
Answering machine messages and voicemail prompts are very different too. Phone company messages are also complicated. Some announcements start with a disconnected beep sound, others with a different beep, and the rest do not even have one.
The system has to make a decision in real time
The system has to analyze the audio stream in real time so it can respond as soon as possible. This in certain degree limits what kind of algorithm the system can deploy. It is much harder to do it in real time with partial audio streams.
The system does make mistakes
Voicent has spent a lot of development time to improve the accuracy. Our products has been on the market for years and we have collected a large amount of data for the prediction algorithm. Voicent system is battle tested in real world and the accuracy is second to none.
However, as you can see, the prediction algorithm is based on statistics data. There is no guarantee the prediction is correct. We can always improve the accuracy and make the system more intelligent, but to reach 100% accuracy is impossible using today’s technology. The best system for prediction is the human perception system. But even humans make mistakes from time to time.
Your telephone line is noisy
The telephone line here refers to traditional phone line or VOIP “virtual line”. Some phone lines have loud static and they are really bad for the prediction algorithm. You should contact your phone company for a better line. Or check your phone wiring, such as really long phone line, too much equipment on the same line, etc.
If you are using a traditional analog phone line, you should also make sure there is no special signal on the line. For example, if you have voice mail service, the indication of new voice mail is a special dial tone on the line. It will sometimes make the outbound call noisy. Call waiting signal also affect the line.
If you are using a VOIP service, the line quality depends on your broadband connection also. If you are download a large file while making phone calls, your voice will be choppy from time to time.
If you use Skype, please see Detection problem when using Skype
Your computer is too slow
If you have an old computer (Pentium II), especially when you are using a multi-line system, the initial delay might be caused by the computer taking too much time for the calculation.
You can use Windows Task Manager to see whether your computer is lack of computation power or lack of memory. For details, please see Microsoft Windows’ document.
Useful diagnose tool
You can use the Record Initial Dialing to understand what is “heard” by the program from the line.
Please see more information on Part II of this article.
