Introducing Pheme: A new speech generation model from PolyAI
At PolyAI, we’ve been creating voice assistants for enterprise customer service since 2017. One of the key factors we’ve found...
Research
Creating a more accurate ASR model for customer service than Google
Automatic Speech Recognition (ASR) or Speech-to-Text is the process of transcribing spoken utterances into text. It enables voice assistants to...
Generative speech – scaling universal vocoder to new limits
In artificial intelligence and speech synthesis, the quest for more natural and realistic voice interactions is a priority. At PolyAI,...
Applications of ChatGPT in enterprise conversational AI
The buzz around ChatGPT is undeniable. But many conversational AI vendors are telling the same story – ChatGPT is unsuitable...
Modular intent design: A more effective way of understanding language
Unlike open-domain dialogue systems which focus on free-flowing conversations with no particular objective, Task-Oriented Dialogue (TOD) systems are designed with...
PolyAI maintains lead over IBM Watson Assistant and other popular language understanding models
In December 2020, the team at IBM published a blog post and technical paper in which they benchmarked the performance...
PolyAI’s ConveRT model outperforms BERT and GPT-based models in Salesforce research evaluation
In a recent evaluation by Salesforce Research, PolyAI’s ConveRT model performed top across a range of metrics, while using a...
ConVEx: How PolyAI created the most accurate value extractor on the market
We’re thrilled to announce our recently published paper on the PolyAI ConVEx framework. Our new technique, ConVEx (Conversational Value Extractor),...
Intent Classification with Geometrically-Friendly Embeddings
At PolyAI, our conversational agents are powered, in part, by machine learning models that detect the intent behind what a...
Our Voice Assistant Spoke to Google Duplex. Here’s What Happened…
This summer, Google has been deploying its AI voice assistant called Duplex to call bars and restaurants in order to...
The Truth About End-to-End and Unsupervised Learning
There’s a common perception that creating an AI agent can be a simple process of end-to-end learning, where labelled data...
PolyAI Encoder Model: Understanding as a Service
One of the fundamental building blocks of conversational AI is understanding natural language. AI agents need to understand what a...
We’re building the most accurate intent detector on the market
Intent detection is the task of classifying a user’s intent. For example, in the hospitality industry, intent categories might be...
Using conversational voice AI to manage ID&V in contact centers
We’ve recently been working with large contact centers to explore the best potential opportunities for conversational voice AI for their...
Towards Composing Multilingual Conversations
Speaking more languages simply means reaching more people. This statement is equally true when it relates to humans or to...
A Repository of Conversational Datasets
Progress in Machine Learning is often driven by large datasets and consistent evaluation metrics. To this end, PolyAI is releasing...
The Magic Triangle of Dialogue Data Collection
Data is the driving force behind all our machine learning models. Although the word data itself buzzes a lot, the...
Neural Language Understanding of People’s Names
This is a deep-dive into one of the problems we face when we model dialogue: understanding mentions of people’s names...