Professional Documents
Culture Documents
Speech Analytics-Brochure
Speech Analytics-Brochure
Speech
Analytics
(RTSA)
R E A L-T I M E S P E E C H A N A LY T I C S
Evaluation
By defining “good” and “bad” phrases, you can determine This evaluator automatically categorises calls based on This is used to evaluate the volume
how many desired or undesired expressions your agents the occurrence and proximity of predefined keywords of the agent and/or customer.
are using. This is especially useful when there is a speci- and phrases. It may also be used as “next-best-offer” This feature distinguishes between
fied “brand language” which agents are required to use evaluator for automatically showing hints to agents in times when there is talking and
or when receiving customer complaints. RTSA records specific situations. when there is no talking (and only
the number of used ‘good’ and ‘bad’ phrases and using a • Automatic categorisation of calls using predefined background noise can be heard)
statistical algorithm calculates a score for the call. phrases and keywords and whether the talking is too loud
• Displays hints for next best offering when a specific or too low. Based on this, general
GOOD PHRASES EVALUATOR category is detected information is displayed regarding
the recording volume of the call
• Count how add-ons have been sold per product CLEAR SPEAKING and the positioning of the headset
• Verification whether desired/promotional phrases microphones. If the customer
have been used RTSA is able to assess if the agent is speaking perceives the agent as “too loud”
• Visual positive feedback when correct brand names comprehensively by evaluating both the pronunciation or “too low”, the agent can see
are used to introduce new products and services of the phrases to be checked and the rate of speech. this immediately and adjust the
• Correlation of promotional phrases and sales rates The agent-specific statistics that are based on these microphone position of the headset
evaluations are ideally suited for use in training and for accordingly.
BAD PHRASES EVALUATOR reviewing the effectiveness of coaching.
Evaluation
This evaluates whether the agent and/or customer Evaluates the dynamic range of a call. It is analysed,
allow each other to finish speaking. If one side does not whether the voice can be heard in a natural dynamic
let the other finish speaking and interrupts the person range. “tiny” speech marks at beginning of dull should
instead, this produces a negative evaluation. The longer be as shown here. “dull” speech marks at beginning of
and the more often the other person is interrupted, dull should be as shown here. A notice can be displayed
the worse the evaluation score. This evaluation can on the LiveClient to the agent once a configured limit is
be utilised from the customer’s and/or the agent’s reached.
perspective (in other words, the system differentiates META DATA
between who interrupts whom). This evaluator points
out typical mistakes, such as “getting rid” of a customer Incorporate additional data and KPIs into the Vocal
by trying to say goodbye while the customer is still Coach: any external meta data can be managed and
talking. Furthermore, the feature provides information evaluated by the Analyzer,. so that you can expand the
about whether the customer frequently interrupts the reports of individual conversations by AHT, success
agent, which indicates that the customer has already rates and many more. Both, the meta-data as well as the
understood the topic or is not interested in general. data of the conversation can be analysed in real-time
and be assigned with a score between 0 and 100.