This week my research continues on Text-To-Speech Plug Ins, Speech-To-Text Plug Ins and also Predictive Dialing. Other than that, I also did some researxh on TTS and STT Plug Ins using Asterisk. The main reason of this task is to find and survey the prospective products that can be used by our companies. It is also purposed to survey the price and usage of these products and determine the benefits of this product for the company.
TEXT-TO-SPEECH (TTS) SOFTWARE
Text-to-speech (TTS) is a type of speech synthesis application that is used to create a spoken sound version of the text in a computer document, such as a help file or a Web page. TTS can enable the reading of computer display information for the visually challenged person, or may simply be used to augment the reading of a text message. Current TTS applications include voice-enabled e-mail and spoken prompts in voice response systems. TTS is often used with voice recognition programs. There are numerous TTS products available, including Read Please 2000, Proverbe Speech Unit, and Next Up Technology's TextAloud. Lucent, Elan, and AT&T each have products called "Text-to-Speech."
In addition to TTS software, a number of vendors offer products involving hardware, including the Quick Link Pen from WizCom Technologies, a pen-shaped device that can scan and read words; the Road Runner from Ostrich Software, a handheld device that reads ASCII text; and DecTalk TTS from Digital Equipment, an external hardware device that substitutes for a sound card and which includes an internal software device that works in conjunction with the PC's own sound card.
Figure : Demo of TTS that provides visual.
TTS are normally used to read out from a text. It can be used to read text from a Word file, Powerpoint file or even Excel file. IT is very useful from who are difficulties in seeing and so on. However, in the context of my company, TTS is used to create human like voices to be used as operator person whenever you call a company.
My job is to edit these voices using the WAVEPAD EDITOR software that we have learnt from week 1 of my industrial training. Certain TTs does not provide the exact voice that we wanted. This is why we can use the wavepad editor to change the pitching, amplitude and other elements of the voice. Using this editor, I am allowed to attach or detach certain voices to or from each other.
Figure : Process that involved in TTS
SPEECH-TO-TEXT (STT) SOFTWARE
Ability of computer systems to accept speech input and act on it or transcribe it into written language. Current research efforts are directed toward applications of automatic speech recognition (ASR), where the goal is to transform the content of speech into knowledge that forms the basis for linguistic or cognitive tasks, such as translation into another language. Practical applications include database-query system information retrieval systems, and speaker identification and verification systems, as in telebanking. Speech recognition has promising applications in robotics, particularly development of robots that can “hear.”
However, in my company we seldom use this software as the process of my work does not involve this software. this software is not widely used although its beneficial to people who are unable to write or to make it easier for deaf people to understand certain conversation to be in back and white copy..!!!
Figure : The process of changing speech-to-text.
Figure : Application on STT
PREDICTIVE DIALING
A predictive dialer is a telephone control system that automatically calls a list of telephone numbers in sequence, screening out no-answers, busy signals, answering machines and disconnected numbers while predicting at what point a human caller will be able to handle the next call. Predictive dialers are commonly used for telemarketing, surveys, appointment confirmation, payment collection and service follow-ups. Sellers of predictive dialer systems claim that they greatly increase caller productivity. The phone calls you receive from "no one there" are often predictive dialer calls in which a manual caller isn't ready yet. Not to be confused with an automatic dialer, a predictive dialer is programmed to predict when a human caller is available to pick up a call. Predictive dialers can also measure the number of available agents, available lines, average handle time and other factors to adjust outbound calls accordingly. This measurement delivers a high level of mathematically efficiency to use in call centers. A related system is a lead generator, which dials a list of telephone numbers and, when a live voice answers, delivers a recorded message.
Figure : Predictive dialing. It will guess which is online at the particular time so that the caller do not have to wait long to get to an agent.
This mode is widely used because it is, without doubt, the most productive for agents. Predictive dialers use historical statistics and sophisticated algorithms to calculate agent availability. Thus, based on past trends, the solution will know exactly how many dialing attempts and how much time are required to reach a live contact, as well as exactly when an agent will become available to take that next outbound call. Therefore, the dialer can start dialing to reach the next available customer/prospect even before an agent becomes available and connect this live contact as soon as or shortly after an agent becomes available. Since the predictive algorithm analyses a number of factors, including the number of available telephone lines and agents and the probability of a call not being completed (e.g., busy signal, no answer, etc.), it becomes impossible to establish a "magic" rule to determine the number of agents required for the planning algorithms of the predictive mode to select the perfect rhythm. However, a dynamic rule can be constructed according to three closely linked criteria; in order of importance, these are:
- call length
- length of after-call wrap-up
- the number of agents for one campaign and its sublists
When properly used, predictive dialing can have a dramatic effect in the contact center. Normally, the busy rate for agents between manual and predictive modes increases by 30% to 60%.
Figure : Difference between wait time and talk time using predictive dialing and also manual dialing.
No comments:
Post a Comment