Home » Solutions » Voice analytics


Silence Periods

Xdroid’s VoiceAnalytics solution is an Automated Performance Management platform for contact centers based upon speech and True Emotion Analytics. It uses machine learning and AI capabilities in combination with CRM and NPS data to give a deep insight into the quality and performance of the contact center as a whole as well as of individual agents. In addition, it is an effective commercial asset for customer retention.

Improve call center performance management with speech and emotion recognition, advanced real-time analytics, CRM integration, TNPS prediction, and Machine Learning.

Xdroid’s VoiceAnalytics uses machine learning and artificial intelligence to identify and measure true emotions based on speech styles, not on keywords.

Xdroid analyzes speech blocks of a few seconds, and when an emotion different than neutral is detected, the system puts this emotion into one of four possible categories; happy, disappointed, displeased or uncertain and assigns a value to it. The tone of voice, volume, articulation, and speed are also taken into account, the larger the value, the stronger the emotion, thresholds can be defined to adapt to cultural differences in the way people express themselves.
Every speech block of the conversation yields a so-called overall Emotion Index for the complete call. The Emotion Index allows for ranking these calls from a high to a low displeased Emotion Index. This way the score of a call can be compared to the average value across all calls of the contact center, or to the individual operator’s score to the group average etc.

A weighted sum is taken over all the emotion values of every speech block of the conversation to yield a so-called overall Emotion Index for the complete call. The Emotion Index allows for ranking these calls from a high to a low displeased Emotion Index. This way the score of a call can be compared to the average value across all calls of the contact center, or to the individual operator’s score to the group average, etc.

The most important benefits of using Xdroid’s VoiceAnalytics are:

Increase customer retention

Customers can start retention workflows by filtering out the most displeased customers. Immediate and efficient reactions to the displeased customers improve both customer retention (and by that reducing the churn) and quality of customer handling.

Reduce legal cases

Use keyword and emotion filters to locate threatening calls that probably end up in authority or legal case. Reduce the number of these harmful cases by calling back the customer and handle the situation in a proper way before it’s too late. This helps to maintain the reputation as well.

Boost sales conversion

Increase sales conversion rates by analyzing successful and unsuccessful sales attempts. Reveal differences in speech style, keywords, use of the companies value propositions and in other meaningful metrics. The method can be applied to either direct outbound sales or to offers during inbound calls.

Reduce agent turnover

Increase loyalty and give better training of contact center operators by providing them transparent, objective feedbacks, rating, and coaching about their performance Use regular reports and automatic suggestions in order to keep them well-trained and maintain consistent quality management.

Objective, Automated coaching

Provide a transparent and objective track of each agent’s progress. Increase your operator’s training level and efficiency by using automated feedback on each key metrics (intonation, speed, dominance, music periods, speech volume, etc.) so agents can quickly realize what they can do to be more efficient.

Improve call-handling efficiency

Reduce unnecessary music and idle times during call handling and analyze root causes of them. Decrease average call times and increase the quality of call handling in parallel. There might be lots of differences even at the operator level, so track and analyze each call.


Xdroids InsightLearning module, based on artificial intelligence, can perform predictive analysis across all conversations to identify trends and patterns in the analytics data. This is especially important for conversations that ended with a customer starting legal actions or for fraud attempt related conversations, etc.

How it works?

Xdroid’s PredictiveAnalytics helps to recognize the factors that played a crucial role in the conversations that ended badly. It takes CRM data and speech characteristics into account, as well as complex relationships that, without MachineLearning, would be left uncovered.

The system will automatically generate rules that can be applied to new conversations, and alerts which can be set for conversations that meet these criteria, so that the right people can be notified in time and can take appropriate action.

With this approach, new conversations that show a particular trend can be identified far more efficiently. For instance; when 5% of the customers have cancelled their contract in a week, machine learning will identify the difference in patterns between the 5% “negative” and 95% “positive” calls.
The machine learning module will analyze and show that a subset of the calls meets certain criteria like; the length of a call, emotion index level, keyword hits, etc. and it will also show that 10,8% of this group of customers ended up cancelling their contract.

This means that when a new conversation meets these rules, the likelihood that this call will also end up with the customer cancelling the contract is 10,8%. Which is 2,16 times higher than the average of 5%.

By combining multiple rules, machine learning can achieve even higher efficiency, so predicting the customer’s behaviour is even more accurate.
The platform’s alerts function can be assigned to these rules to notify the right people in time, so they can take appropriate action.
Contact centers can easily and quickly get an idea of what factors play a key role in certain behaviour or events, like contract cancellation or Net Promoter surveys.

VoiceAnalytics quantitative examples:

VoiceAnalytics is deployed at market leading companies in the fields of banking, insurance, energy and telecommunications. Xdroid’s customers have testified about the positive ROI they have experienced for their business as a result of using and adopting VoiceAnalytics.

Measure and reduce unnecessary music and silence periods during customer handling. Increase agent’s and overall call center effectiveness.


Increased call productivity by 4% by reduced silence and music periods.
On average 20 sec lower call time
Over 2500 agent hours became available for handling other customers


Insurance company, 100 agents 4 weeks of lead-in time 50.000 calls per month analyzed

Identify customers who are willing to cancel the contract by using keyword and emotion detection. Start customer retention workflows at certain situations where the agent did not.


Successfully identified additional at-risk customers by 30,4%
More than 400.000 EUR revenue retained


Telecommunication, 200+ agents
8 weeks project lead-in
200.000+ calls per month analyze

Find out how Xdroid’s Voice- and TextAnalytics can improve
the overall performance and quality of your contact center.

Request a demo

Start typing and press Enter to search