Abstract
This paper analyses the performance of different types of Deep Neural Networks to jointly estimate age and identify gender from speech, to be applied in Interactive Voice Response systems available in call centres. Deep Neural Networks are used, because they have recently demonstrated discriminative and representation capabilities in a wide range of applications, including speech processing problems based on feature extraction and selection. Networks with different sizes are analysed to obtain information on how performance depends on the network architecture and the number of free parameters. The speech corpus used for the experiments is Mozilla’s Common Voice dataset, an open and crowdsourced speech corpus. The results are really good for gender classification, independently of the type of neural network, but improve with the network size. Regarding the classification by age groups, the combination of convolutional neural networks and temporal neural networks seems to be the best option among the analysed, and again, the larger the size of the network, the better the results. The results are promising for use in IVR systems, with the best systems achieving a gender identification error of less than 2% and a classification error by age group of less than 20%.
Highlights
This paper deals with the design of algorithms to classify speakers into age and gender groups, to be applied in call centres with ‘Interactive Voice Response’ (IVR) systems
Block-level results are obtained by evaluating one-second audio blocks independently, while file-level results are obtained by averaging the outputs of all blocks that make up each file before computing the metrics
These results indicate that when the system is implemented in a real IVR system, around 80 % of the callers will be routed to the correct specialised agent
Summary
This paper deals with the design of algorithms to classify speakers into age and gender groups, to be applied in call centres with ‘Interactive Voice Response’ (IVR) systems. Most of the costs are spent on human resources, so a great effort has been made to optimise the use of agents, considering they are not homogenous, and have different experience and skills, handling customers requests with different speeds [40] For this purpose, different routing strategies are applied in IVR systems, like direct routing, self-service routing, skill-based routing, or data-directed routing. The prediction uses historical data from agents and customers, or other information that could be obtained from the customer voice, such as emotions, age and gender Both information extraction and best match prediction can be implemented with machine learning techniques [20]. This paper presents a framework to jointly identify speakers’ gender and classify them into age groups, designed to be applied in IVR systems.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
