Sensors, Speech and a Data Deluge.
Our experiments with tracking face to face interaction, developing speech algorithms and building wearables.
“Creativity comes from spontaneous meetings, from random discussions.”
In our last post I wrote about the spontaneous meetings, casual collisions and serendipity great spaces create – whether they be office spaces, town centres or cities – and how its these environments and the creative conversations that take place within them that help breed creative clusters and innovative high growth companies.
While there’s quite a bit of high level data and research on urban, demographics and economic trends, we’re still left wondering how do you quantify the clustering of people, casual collisions and serendipitous meetings? How do you track the density of social interactions and its impact on value creation? Especially if you want to track these types of interactions on an individual level with some sort of granularity, and ideally in a passive manner that’s not open to subjective bias and in a somewhat real time manner (rather than post event surveys).
“Density, the clustering of creative people – in cities, regions, and neighborhoods – provides a key spur to innovation and competitiveness.”
I think we all intuitively know that face to face conversations, social density and spontaneous interactions are enjoyable and incredibly valuable, but in todays data driven world unless we can quantify, compare and correlate these interactions with other metrics that more naturally appeal to the age of capitalism how do we establish the true worth of random discussion?
With these sorts of questions in mind we where excited to come across the work of Alex Pentland, director of MIT’s Human Dynamics Lab. He’s spent many a year looking at human computer interaction and a good part of that tracking human interaction patterns using either smartphones or what he calls a Sociometric Badge – basically a microphone, infrared transmitter, wifi and receiver and accelerometer that hangs around the neck of a person so you can track their speech, movement and with the IR and wifi who they are in close physical proximity too. The badges and mobile apps allow realtime tracking not only of the spontaneous meetings and random discussions, but also the energy and engagement of the conversation as measured by metrics around the volume and tone of speech. Additionally the device’s infrared sensor passively tracks the “brief and passive contacts made going to and from home or walking about the neighborhood”, the type of interactions post war MIT psychologists Festinger, Schachter, and Back found are key to forming friendships. These individual features can then be aggregated to quantify the social density and clustering of people around time and place.
We were pretty impressed with some of the outcomes they had from tracking social interactions and speech, so last October we started working on building out a similar device for running our own experiments. Working with two electronic engineers we designed a simplified speech and proximity sensor, shortly after we got an invite to attend interviews for YCombinator’s Winter14 round. At that point it was just a bundle of cords so we packaged up the electronics in a box of sorts.
A few months later in January we were really happy to be plugging in our first set of thirty speech and proximity sensors. This latest set looks a lot sexier and includes a microphone, infrared transmitter and receiver, along with storage for both. The device produces two files: a wav file of audio, and infrared data (with ID of other device seen) in a csv format.
Alongside the hardware our CTO Mike has been working on several algorithms for analysing the audio. This bundle of algorithms clean the audio of background non-verbal noise, then spot the human speech within all the sounds, breaks the speech into chunks of speech and identifies patterns within the speech to determine how many different speakers there are and at what point they spoke. We also have another algorithm that matches these ‘speakers’ against a voice print so we can know who is who – to do this we need a bit of training data on that person and have been collecting 30 second samples to train the algorithm on. We then have another set to work out colocation – who is speaking to who, who is a part of the conversation and over what duration. To do this we compare the wavelengths across the recordings from each separate device, and work out the likelihood that the two devices are recording the same sound all be it at different volumes (due to differing proximity to the sound source).
From this we extract a range of individual metrics for that person ie. tone, volume, variation, speaking time, listening time, with who, for how long, etc and then aggregate them up to create network graphs and other funky visualisations.
There is still a fair amount of work to be done to automate the cleaning, processing and analysis of the speech and interaction data but nevertheless we have run our first two technology pilots, one with Startup Weekend here in Perth and another with Australia’s top tech accelerator, Startmate, in Sydney.
At Startup Weekend there was about 77 participants who then formed ten teams and worked on their app ideas from 7pm Friday night to around 6pm Sunday. We were able to track 29 of these participants with the wearable sensor across 5 teams. The remaining participants we recorded via desktop mics that sat in the middle of each team table. We also recorded all the pitches both before the weekend and the final pitches to the judges. Our intention with the Startmate pilot was to compare the aggregated team interaction patterns to performance in the competition as measured by the judges scores at the end of the three days. We’ve already visualised some of the IR data to show the proximity patterns for those wearing the sensor, and are still working on analyzing the 50GB of audio data we collected. We’ll update you on that as we proceed.
Startmate, the tech accelerator was a similar situation, but there are only around 30 people in the 2014 batch. We had about half the cohort wearing the sensors while the other half we’re out of the building selling. The numbers on this pilot aren’t great for statistical purposes but it’s been a good opportunity to see how the device works in the wild. We also recorded all the companies pitching so we’re building up a good bank of audio recordings on people pitching/selling ideas and others ‘buying’ or not. A great corpus to compare against speaking traits.
Still plenty of work to be done in pulling meaning from the data but it’s good to have the sensors in the water and see them quantifying some of the real world social capital we all intuitively know is extremely valuable.
Our next steps are to tweak version one a little then produce a batch in the low hundreds for some of our larger pilots. At this stage we aren’t sure to what point we will develop the wearable device to, or how much of the valuable speech tracking can be done by a smartphone - we’re using the pilots to test this. But we certainly think this data is vital for innovative organisations to quantify critical value creating behaviours.
If your interested in us mapping communication and interaction patterns at your work place shoot us an email and we’ll arrange a not so random meeting.