How to use speech recognition in business

A revolution is coming to the market for call tracking: we are on the verge of introducing speech recognition technology. Recently, it has found application in American services, how soon the trend will come to Russia, what benefits business owners will receive, says Yevgeny Vlasov, CEO of Calltouch.

Background
')
First, let's look at what speech recognition is. In the scientific community, the process of converting a speech signal into digital information (for example, text data) is so called. The antithesis of technology are talking robots that convert digital information into speech signal.

The first speech recognition device appeared in 1952, it understood the numbers spoken by man. In the early 1990s, programs were released that allow people with disabilities to work with text. But the technology was not widely spread, because the recognition was inaccurate due to several problems:

• arbitrary, naive user;
• spontaneous speech, accompanied by agrammatism and "speech debris";
• acoustic interference and distortion;
• speech interference.

In addition, the same word may sound differently, if a person speaks with an accent, incorrectly places stress, changes the pace and volume of speech. Sometimes these details affect understanding between people, not to mention computers.

Nevertheless, the programs gradually learned to recognize the voice and the first language they understood became English: it is widely spoken, fairly simple (simpler than Russian and Chinese), and therefore requires less complex mathematical algorithms. The market for Western IT technologies grew rapidly and, thanks to high competition, speech recognition soon became widely used in business.

Conversation business

In Russia, only Yandex has so far achieved the most success: in 2013, the company launched the cloud-based technology SpeechKitCloud, which helps to synthesize and recognize speech.

Synthesis occurs due to the statistical approach in acoustic modeling. Simply put, the program forms a new voice based on the intonations of living people. This allows you to give an artificial speech emotional coloring (good, evil, neutral) or to endow with sexual characteristics (man, woman). At the time of this writing, the service offered free testing for a month, a further estimated cost of $ 5 per 1000 requests.

Unfortunately, large companies are not in a hurry to use this technology to its fullest, but there are still enthusiasts. For example, Oktell, a Russian developer of call center automation systems, uses SpeechKitCloud to create greetings and voice menus that callers hear, as well as recording answers to frequently asked questions. The technology is applied simultaneously with the work of the call center, reducing the burden on operators.

Colleagues from Repka.UA almost managed to replace people with machines. They connected SpeechKitCloud speech synthesizer and an online store accounting system, developed an order confirmation script, as a result, a robot Christine appeared, which automatically checks the availability of goods and its price upon receipt of an order, calculates the date of shipment and calls the customer for confirmation.



If a person has questions, the call is transferred to the call center operator. Naturally, at first Christina’s speech recognition rate was low, in unusual situations she couldn’t replace a person and joined the work during the peak of incoming calls.



But, thanks to the creation of its own speech model, the company managed to increase its accuracy; and now the cost of a robot is 5 times lower than the operator and 8 times lower than the external call center.

Another feature of SpeechKitCloud is speech recognition, allowing customers to place an order by phone in automatic mode. Today, in addition to standard answers (“issue”, “delivery”, “confirm”), the technology recognizes such phrases as “let's arrange”, “I don't know”, “take it myself”, “okay”. At the same time, the system recognizes about 82-95% of Russian speech, depending on the original sound, coding quality, intelligibility and speech rate, complexity of phrases and their length. The use of technology, as in the case of speech synthesis, first of all reduces the load on the call center, and in the future, subject to quality improvement, can completely replace it.

Near future

Now systems are used only for receiving and distributing outgoing and incoming calls. However, we at Calltouch are confident that this is not the limit, and by the end of the year we plan to complete the integration of speech recognition technology with a call tracking service, which will allow us to bring the optimization of advertising campaigns and business processes in general to a new level.

Take for example the history of the distribution of calls. Most businessmen today want to learn how to manage the flow of phone calls and separate those who are calling to make a purchase from those who are interested in consulting.

For example, a toy store that advertises in Yandex.Direct, the Yandex Advertising Network (YAN) and the social network VKontakte, I wonder what source brings him calls ending in purchases. Suppose that VKontakte results mainly for those who wish to receive a free consultation, YAN - calls to the service, and Yandex.Direct is selling. In this case, it is worth redistributing budgets in favor of Yandex.Direct, as much as possible while reducing the cost of advertising in social networks. But, not knowing how the calls of potential customers are distributed, this cannot be done.

Today, there are two separation methods:

1. Auto. When you call, the voice system is triggered, which offers to make a choice: the “1” button takes you to the sales department, the “2” button goes to the service center. This information enters the call tracking system and is analyzed.
2. Mechanical . The secretary of the company, realizing that the customer who called has been interested in the purchase, presses the number “1”, if the services of the service are the number “2”. The service marks the first calls as “corrupt”, the latter as “service” and builds the analysis based on this data.

Both methods depend on the human factor. In the first case, the client is inconvenient to perform an additional action (press the buttons), and he will hang up or press another digit. In the second, the secretary may forget to mark the call or “wind up” the result, if, for example, its KPI depends on the number of “sales” calls.

With the advent of technology, the human factor can be eliminated. If you teach the system to understand the keywords that are most often used in advertisements, it will divide them into groups and mark the call as “corrupt” or “service”.

Also, speech recognition will help monitor employees. For example, the company owner has a feeling that subordinates do not modify, are rude to customers or miss calls. This can be checked only in one way - by listening to the recordings of telephone conversations But it will have to spend time and money if you hire an employee to complete the task. Whereas a speech recognition call tracking service will automatically indicate existing problems. To do this, scripts and templates of “correct” communication with customers are loaded into the system and it is determined how many times an employee must say these words. If the program finds them in a conversation, then the manager behaved correctly. On the other hand, call tracking will help identify aggressive behavior or incorrect conversation. Naturally, the method will not give an absolute result, but will help to understand the quality of communication with customers.

After analyzing the information provided by the technology, you can increase sales. For example, the program will reveal words that have never been used in advertising campaigns, but most customers pronounce them when they call the store. It is useful to insert such phrases into ads, this will broaden the audience’s context and bring more effect than ordinary text written by marketers.

Of course, it takes time for Russian call tracking services to learn to understand speech. But there is no doubt that users will appreciate the opportunities that technology will open.

Source: SearchEngines.ru .