Verint Da Vinci AI Research
Our AI Research Publications
At Verint, our team of data and AI scientists are constantly at work to make customer engagement better around the globe through innovation and research. Our researchers hold hundreds of patents, and regularly publish their findings in leading industry and scholarly publications. Their work directly fuels the accuracy, automation, and efficiency that Verint customers rely on every day.
Deception Detection in Conversations Using the Proximity of Linguistic Markers
Contact centers are a potential platform for fraud, and many companies now use an automated system to spot deceptive callers. Here, researchers propose that a Decision Engine detect deceptive conversation based on the proximity of linguistic markers present, which produces a deception score for a conversation and highlights the potential deceptive elements of the conversation.
Verint Researchers: Cornelius Glackin, Nigel Cannings, James Laird, Thea Laird, Marvin Rajwadi
Enhancing Automatic Speech Recognition Quality with a Second-Stage Speech Enhancement Generative Adversarial Network
Speech enhancement is an essential preprocessing stage for automatic speech recognition in noisy conditions; however, the distortion caused by the denoising process may lead to degradation in automatic speech recognition performance. This paper presents a deep learning-based speech enhancement architecture to overcome this issue by applying a second-stage network that deals with distortion noise.
Verint Researchers: Nigel Cannings, Cornelius Glackin
A Deep Learning Speech Enhancement Architecture Optimized for Speech Recognition and Hearing Aids
Due to advancements in the speech enhancement field thanks to deep learning techniques, there is a need to consider the adjustments needed to employ these techniques for real-life applications. Here, we present an optimized deep learning speech enhancement architecture for automatic speech recognition and hearing aids, two key speech enhancement applications.
Verint Researchers: Cornelius Glackin, Nigel Cannings
Investigating HuBERT-based Speech Emotion Recognition Generalization Capability.
Transformer-based architectures have made significant progress in speech emotion recognition (SER). However, most published SER research trained and tested models on data from the same corpus, resulting in poor generalization ability to unseen data collected from different corpora.
Verint Researchers: Cornelius Glackin, Letian Li, Nigel Cannings
A Frequency Bin Analysis of Distinctive Ranges Between Human and Deepfake Generated Voices
Deepfake technology has advanced rapidly in recent years, leading to concerns around security and the need for countermeasures. In this report, researchers analyze the specific locations in the frequency spectrum where distinctions between human and deepfake audio occur.
Verint Researchers: Cornelius Glackin, Nigel Cannings
Responsible and Ethical AI
AI is integral to Verint Open Platform and powers the applications our customers use every day. Verint realizes that advanced technologies like AI can raise important challenges that must be addressed clearly, thoughtfully, and directly. This document highlights Verint’s AI strategy, the principles we follow as we execute on that strategy, and the processes, controls, and guidelines we have put into place to guide our use of AI.
Author: Verint
An Open Intent Discovery Evaluation Framework
Discovering target intents is crucial but often overlooked in dialog systems. Creating labelled datasets is complex and manual. Open Intent Discovery automates grouping utterances and identifying intents. This framework offers various techniques for each discovery step, including human-readable label generation. It also analyzes dataset features to recommend optimal technique combinations, aiding users without exhaustive exploration.
Authors: Ian Beaver, Grant Anderson
Automated Human-Readable Label Generation in Open Intent Discovery
Determining user intent in dialog systems requires large, labelled datasets, which are complex to create. Many works focus on discovering intent clusters but not on generating human-readable labels. This study introduces a new candidate label extraction method, evaluating six combinations of extraction and selection methods on three datasets. Results show detailed labels can be generated from unlabelled data without costly pre-trained models.
Authors: Ian Beaver, Grant Anderson
FCBench: Cross-Domain Benchmarking of Lossless Compression for Floating-Point Data
The database and HPC communities use lossless compression for floating-point data but lack cross-domain evaluation. With HPC’s shift to in-situ analysis, more data is stored in databases, highlighting the need for a unified study. This research evaluates 13 compression methods on 33 datasets, using the roofline model to profile runtime bottlenecks, aiming to guide method selection and development.
Authors: Ian Beaver, Cynthia Freeman
An Adaptive Deep Clustering Pipeline to Inform Text Labeling at Scale
Learn how Verint researchers created a flexible and scalable clustering pipeline that integrates the fine-tuning of language models, a high performing k-NN library, and community detection techniques to help analysts quickly surface and organize relevant user intentions from conversational texts.
Authors: Xinyu Chen, Ian Beaver
Is AI at Human Parity Yet? A Case Study on Speech Recognition
What does it even mean for an AI system to reach human parity? How is progress towards that goal being measured? This article focuses on the current state of speech recognition and the recent developments in benchmarking and measuring performance of AI models built for speech processing.
Author: Ian Beaver
The Success of Conversational AI and the AI Challenge it Reveals
A massive increase in conversational artificial intelligence research and advancement in recent years has enabled systems to produce rich and varied turns in human-like conversations that often rely on crowd worker opinions as the primary measurement of success. The challenge, though, is that evaluation strategies need to mature alongside AI systems that are mature in more “human” tasks that involve creativity and variation,
Author: Ian Beaver
Timevae: A Variational Auto-Encoder for Multivariate Time Series Generation
Recent work in synthetic data generation in the time-series domain has focused on the use of Generative Adversarial Networks. In this paper, we propose a novel architecture for synthetically generating time-series data with the use of Variational Auto-Encoders (VAEs).
Authors: Abhyuday Desai, Cynthia Freeman, Zuhui Wang, Ian Beaver
Automated Conversation Review to Surface Virtual Assistant Misunderstandings: Reducing Cost and Increasing Privacy
With the rise of Intelligent Virtual Assistants (IVAs), there is a necessary rise in human effort to identify conversations containing misunderstood user inputs. Here, we present a scalable system for automated conversation review that can identify potential miscommunications and provide IVA designers with suggested actions to fix errors in IVA understanding, prioritizes areas of language model repair, and automates the review of conversations where desired.
Authors: Ian Beaver, Abdullah Mueen
Experimental Comparison and Survey of 12-Time Series Anomaly Detection Algorithms
There’s a plethora of AI anomaly detection methods across domains, which can be a burden for AI developers. To reduce this evaluation burden, we present guidelines to intelligently choose the optimal anomaly detection methods based on the characteristics the time series displays such as seasonality, trend, level change concept drift, and missing time steps.
Authors: Cynthia Freeman, Jonathan Merriman, Ian Beaver, Abdullah Mueen
Fine-Tuning Language Models for Semi-Supervised Text Mining
In this paper, we present an empirical study of a pipeline for semi-supervised text clustering tasks. Our proposed method utilizes a small number of labeled samples to fine-tune pre-trained language models. This fine-tuning step adapts the language models to produce task-specific contextualized representations, improving the performance of downstream text clustering tasks.
Authors: Xinyu Chen, Ian Beaver, Cynthia Freeman
Featured Verint Da Vinci AI Researchers
Activating this element will cause content on the page to be updated.
Ian Beaver, PhD
Ian Beaver, PhD is Chief Data Scientist at Verint, where he works to optimize human productivity in contact centers by way of automation and augmentation and improve customer experiences through the application of generative AI. Ian has worked on topics surrounding human-computer interactions such as gesture recognition, user preference learning, and communication with multi-modal intelligent virtual assistants since 2005. He has authored more than 70 patents and over 30 academic publications within the field of AI and regularly serves as a program committee member in many top AI and NLP conferences as well as an associate editor and columnist for AAAI AI Magazine.
Xinyu Chen
Xinyu is a Research Scientist at Verint Systems Inc and a PhD student at Washington State University. His interests are in the field of Natural Language Processing, Parallel Computing, and Graph Theory. His research includes integrating the power of graph theories, parallel computing, and machine learning techniques to solve real-world natural language problems.
Cynthia Freeman, PhD
Cynthia is a Research Scientist at Verint. She holds a BS in mathematics from Gonzaga University, a MS in applied mathematics from the University of Washington, and a PhD in computer science from the University of New Mexico. Her research includes machine learning applications, time series analysis, such as anomaly detection methods, and statistical analysis of contact center data.
Grant Anderson, PhD
Grant is a Research Scientist at Verint and part-time PhD student at Edinburgh Napier University (ENU) in Scotland. He is currently researching applications of large language models and generative AI in contact centers as part of the Da Vinci AI Research group. Prior to this he obtained his BS in Games Development from ENU, where his honors project focused on evolving neural networks for control of vehicles in games.
Karni Gilon
Karni, Director of Analytics, has an MSC from Weizmann Institute in Mathematics and Computer Science and an executive MBA from Tel Aviv University. She served in leading roles in several prominent technology fields, including natural language processing in Citi Innovation Lab and distributed network switching at Broadcom. She studied data science and natural language processing at the Hebrew University of Jerusalem, with several publications.
Samuel (Shmuel) Londner
Samuel (Shmuel) is an experienced NLP researcher. Graduating from the Technion with a B.Sc in Electrical Engineering, Shmuel has extensively researched machine learning and deep learning algorithms across various domains, especially in NLP. In parallel with his work at Verint, he is studying hybrid OCR algorithms at Tel Aviv University, bridging the gap between computer vision and natural language processing.
Ian Beaver, PhD
Ian Beaver, PhD is Chief Data Scientist at Verint, where he works to optimize human productivity in contact centers by way of automation and augmentation and improve customer experiences through the application of generative AI. Ian has worked on topics surrounding human-computer interactions such as gesture recognition, user preference learning, and communication with multi-modal intelligent virtual assistants since 2005. He has authored more than 70 patents and over 30 academic publications within the field of AI and regularly serves as a program committee member in many top AI and NLP conferences as well as an associate editor and columnist for AAAI AI Magazine.
Xinyu Chen
Xinyu is a Research Scientist at Verint Systems Inc and a PhD student at Washington State University. His interests are in the field of Natural Language Processing, Parallel Computing, and Graph Theory. His research includes integrating the power of graph theories, parallel computing, and machine learning techniques to solve real-world natural language problems.
Cynthia Freeman, PhD
Cynthia is a Research Scientist at Verint. She holds a BS in mathematics from Gonzaga University, a MS in applied mathematics from the University of Washington, and a PhD in computer science from the University of New Mexico. Her research includes machine learning applications, time series analysis, such as anomaly detection methods, and statistical analysis of contact center data.
Grant Anderson, PhD
Grant is a Research Scientist at Verint and part-time PhD student at Edinburgh Napier University (ENU) in Scotland. He is currently researching applications of large language models and generative AI in contact centers as part of the Da Vinci AI Research group. Prior to this he obtained his BS in Games Development from ENU, where his honors project focused on evolving neural networks for control of vehicles in games.
Karni Gilon
Karni, Director of Analytics, has an MSC from Weizmann Institute in Mathematics and Computer Science and an executive MBA from Tel Aviv University. She served in leading roles in several prominent technology fields, including natural language processing in Citi Innovation Lab and distributed network switching at Broadcom. She studied data science and natural language processing at the Hebrew University of Jerusalem, with several publications.
Samuel (Shmuel) Londner
Samuel (Shmuel) is an experienced NLP researcher. Graduating from the Technion with a B.Sc in Electrical Engineering, Shmuel has extensively researched machine learning and deep learning algorithms across various domains, especially in NLP. In parallel with his work at Verint, he is studying hybrid OCR algorithms at Tel Aviv University, bridging the gap between computer vision and natural language processing.