<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=145304570664993&amp;ev=PageView&amp;noscript=1">
Call centre header

Apr 26, 2022

Accelerating Conversational AI with Gridspace and Graphcore

Written By:

Gridspace

Join the IPU conversation

Join our Graphcore community for free. Get help and share knowledge, find tutorials and tools that will help you grow.

Join on Slack

Gridspace scans and automates voice calls for contact centers and developers. The company was formed as a collaboration between SRI Speech Labs, the lab behind Siri and Nuance, and a team of Stanford designers and engineers.

As part of a strategy to partner with highly innovative technology companies, Gridspace is collaborating with Graphcore to drive innovation in conversational AI.

Envisioning a contact center automation platform accelerated by IPUs, engineers at Graphcore and Gridspace are working together to explore IPU-based voice applications towards the goal of human parity.

Transformer-Transducer acceleration

In under two weeks, Graphcore - with support from Gridspace engineers - implemented a high performance model, Transformer-Transducer to accelerate the training of over 700G/10k hours of speech with a state of the art word error rate.

The collaboration produced a 100M parameter speech application in a matter of days rather than weeks exploiting the linear scaling of up to 64 Graphcore IPU chips in the BOW POD-64 system.

The Transformer Transducer model for Speech Recognition, achieves SOTA performance on Word Error Rate.

The model consists of transformer layers to encode the audio, LSTM layers to encode text and a Joint Net to combine them. At the head is a Transducer loss that is designed to align the audio and text, which can be of varying lengths.

Off-the-shelf solutions

This is one of many examples of the out of the box performance of the Poplar SDK developed by Graphcore. In addition, Graphcore has released other off-the-shelf tooling and examples which you can find easily and extend for different datasets and domain-specific tasks (e.g. earning call dataset, other language corpora).

As a result of the easy-to-use and easy-to-integrate examples, our time-to-value is improved by the speedup from the hardware and agility of development iterations.

We are looking forward to continuing our excellent collaboration with the innovators in machine intelligence in order to create the next breakthroughs in conversational artificial intelligence.

 

A version of this blog first appeared on the Gridspace website.