The latest
To measure the performance of Conversational AI, we need more strict, better quality benchmarks
For conversational AI to advance, the broader scientific community must be able to work together and explore with easily accessible state-of-the-art baselines for fair performance comparisons. Read more

Suwon Shon, PhD
Senior Speech Scientist at ASAPP
A contact center case study about call summarization strategies
Is your call summarization strategy failing you? Learn from a large enterprise contact center’s mistakes. Read more

Gonzalo Chebi, PhD
Data Scientist
How to Understand Different Levels of AI Systems
Understanding the level of an AI system can help predict how the system will change over time – whether it will continuously improve, remain the same, or even degrade. Read more

Michael Griffiths
Data Scientist, ASAPP
Bringing State of the Art Speech Transcription to CX
End-to-end architecture improves the scalability and performance of machine learning models for speech transcription to serve enterprise contact center needs better. Read more

Prashant Sridhar
Engineering Manager
Wav2vec could be more efficient, so we created our own pre-trained ASR Model for better Conversational AI.
Wav2vec 2.0 is arguably the most popular approach for using self-supervised training in speech, but it could be more efficient. We introduce SEW for better efficiency and performance. Read more

Felix Wu, PhD
Research Scientist at ASAPP
Designed to be proficient on day 1
By combining an intuitive user experience with AI-driven recommendations, you can radically improve the onboarding process. Here’s our approach to making agents successful, faster. Read more

Brad Stell
VP, Product Design
How anomaly detection helps you handle the unexpected
CX teams can identify and react to unexpected customer behavior faster using ASAPP anomaly detection. Learn what makes our models so effective. Read more

Sam Altschul, PhD
Machine Learning Scientist, ASAPP
The keys to CX success in 2022 (and beyond)
The new year brings new challenges for CX organizations. Here are four real ways teams are succeeding during these uncertain times. Read more

Michael Lawder
Chief Experience Officer, ASAPP
GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation
New ASAPP research introduces an orthogonal technique that augments existing data to train better out of scope detectors operating in low-data regimes. Read more

Derek Chen
Research Scientist at ASAPP
Learning to recommend what agents should do
Are your ML models learning the right things? Here’s what we discovered when we took a closer look at what agents do vs. what they should do in one situation. Read more

Chris Fox
Staff Machine Learning Engineer