Artificial intelligence (AI), test to speech (TTS), and audio tours
Frits Polman • nov 18, 2021
Artificial intelligence (AI) is a concept that lots of people will have heard of by now. Many well-known platforms such as LinkedIn, Facebook, and Just Eat already use AI systems which are self-learning and automatically improve. While this offers many advantages, it also has a rather scary side: the programmer no longer knows exactly what the system has learned. More on that later...
Text to speech
As you know, I’m a huge fan of technology – and therefore also of AI. I’ve been wondering for years how we can use AI on our platform for audio tours. We’ve found some wonderful examples, and one that I’ll be discussing today will soon be available to all our customers worldwide: text to speech (TTS).
All of us at Guide-ID have the same mission: to tell as many stories as possible worldwide. That’s why we’ve created the world’s easiest-to-use audio guide. We use audio to help people to discover more about what they see, without any unnecessary distractions. And that requires audio – a lot of audio.
No more time-consuming processes
This audio is usually recorded in professional studios and narrated by professional voice-over actors. While this produces fantastic audio, it’s also a laborious, time-consuming, and expensive process. This is a hurdle for many museums, and even the richer ones often choose to produce audio in one or two languages only. That means some visitors listen to an audio that isn’t in their native language. Many museums can’t do any production at all and don’t offer any audio tours. This situation is changing thanks to text to speech, which – as the name suggests – automatically converts text into speech.
As you know, I’m a huge fan of technology – and therefore also of AI. I’ve been wondering for years how we can use AI on our platform for audio tours. We’ve found some wonderful examples, and one that I’ll be discussing today will soon be available to all our customers worldwide: text to speech (TTS).
All of us at Guide-ID have the same mission: to tell as many stories as possible worldwide. That’s why we’ve created the world’s easiest-to-use audio guide. We use audio to help people to discover more about what they see, without any unnecessary distractions. And that requires audio – a lot of audio.
No more time-consuming processes
This audio is usually recorded in professional studios and narrated by professional voice-over actors. While this produces fantastic audio, it’s also a laborious, time-consuming, and expensive process. This is a hurdle for many museums, and even the richer ones often choose to produce audio in one or two languages only. That means some visitors listen to an audio that isn’t in their native language. Many museums can’t do any production at all and don’t offer any audio tours. This situation is changing thanks to text to speech, which – as the name suggests – automatically converts text into speech.
From unbearable to pleasant to listen to
Until a year or two ago, the level of TTS was unbearably bad: we’re all traumatised by those tinny, robotic voices. But then came a tipping point in AI. Google, Microsoft, and Amazon had reached the critical amount of data that allowed the acceleration of the algorithm. From that moment on, the voices quickly became better – much better. So, we decided to do a test with real visitors and assess their experience. Our most recent TTS baptism of fire was in Amsterdam’s Nieuwe Kerk, where English-speaking visitors were given an automatically generated audio tour. And now the data...
A positive test result
Looking at recent years, we know that visitors who use English-language audio guides at Nieuwe Kerk listen to, on average, slightly fewer stops than Dutch-speaking listeners. This is based on audio tours with professionally recorded voices in a studio. The percentage for the English-language studio versions is 90% compared with the Dutch-language studio versions.
Visitors who listen to the TTS versions in English listen to just under 80% of all stops (compared with visitors who listen to the studio versions in Dutch). So, it’s not a huge difference! What’s more, the stops they listen to are listened to just as long as the Dutch studio versions. Basically, the visitors’ listening behaviour is almost equal between audio recorded in studios and TTS audio.
Audio content for everyone
This is pretty significant, as it enables us to offer all museums low-cost audio content on the spot, in all languages, without weeks of production time. It also takes all the hassle out of making additions and adjustments. Simply change the text, and you’re done. Want to add temporary content for an exhibition? Ta-dah! The algorithm will still make some mistakes from time to time – after all, the programmer no longer knows what the system has learned (or not). But these errors can be corrected manually. But are the voices all top-quality? No, as that requires more money and more patience. But for 99% of museums and their visitors, this is a fantastic development.
Until a year or two ago, the level of TTS was unbearably bad: we’re all traumatised by those tinny, robotic voices. But then came a tipping point in AI. Google, Microsoft, and Amazon had reached the critical amount of data that allowed the acceleration of the algorithm. From that moment on, the voices quickly became better – much better. So, we decided to do a test with real visitors and assess their experience. Our most recent TTS baptism of fire was in Amsterdam’s Nieuwe Kerk, where English-speaking visitors were given an automatically generated audio tour. And now the data...
A positive test result
Looking at recent years, we know that visitors who use English-language audio guides at Nieuwe Kerk listen to, on average, slightly fewer stops than Dutch-speaking listeners. This is based on audio tours with professionally recorded voices in a studio. The percentage for the English-language studio versions is 90% compared with the Dutch-language studio versions.
Visitors who listen to the TTS versions in English listen to just under 80% of all stops (compared with visitors who listen to the studio versions in Dutch). So, it’s not a huge difference! What’s more, the stops they listen to are listened to just as long as the Dutch studio versions. Basically, the visitors’ listening behaviour is almost equal between audio recorded in studios and TTS audio.
Audio content for everyone
This is pretty significant, as it enables us to offer all museums low-cost audio content on the spot, in all languages, without weeks of production time. It also takes all the hassle out of making additions and adjustments. Simply change the text, and you’re done. Want to add temporary content for an exhibition? Ta-dah! The algorithm will still make some mistakes from time to time – after all, the programmer no longer knows what the system has learned (or not). But these errors can be corrected manually. But are the voices all top-quality? No, as that requires more money and more patience. But for 99% of museums and their visitors, this is a fantastic development.
Machine translation: a matter of time
The next step is to add machine translations. The quality of machine translation has also skyrocketed over the last two years, and AI has played a part. We’re not quite there yet, but soon you’ll only need to enter texts in one language. At Guide-ID, we automatically make sure that all your visitors can listen to the stories in their own language the next day. It’s our way of making stories accessible for everyone.
Request a demo (or experience it yourself!)
Want to experience it yourself? Drop by Nieuwe Kerk in Amsterdam or send me a personal message. I’ll get the demo sent to you!
This is pretty significant, as it enables us to offer all museums low-cost audio content on the spot, in all languages, without weeks of production time. It also takes all the hassle out of making additions and adjustments. Simply change the text, and you’re done. Want to add temporary content for an exhibition? Ta-dah! The algorithm will still make some mistakes from time to time – after all, the programmer no longer knows what the system has learned (or not). But these errors can be corrected manually. But are the voices all top-quality? No, as that requires more money and more patience. But for 99% of museums and their visitors, this is a fantastic development.
The next step is to add machine translations. The quality of machine translation has also skyrocketed over the last two years, and AI has played a part. We’re not quite there yet, but soon you’ll only need to enter texts in one language. At Guide-ID, we automatically make sure that all your visitors can listen to the stories in their own language the next day. It’s our way of making stories accessible for everyone.
Request a demo (or experience it yourself!)
Want to experience it yourself? Drop by Nieuwe Kerk in Amsterdam or send me a personal message. I’ll get the demo sent to you!
This is pretty significant, as it enables us to offer all museums low-cost audio content on the spot, in all languages, without weeks of production time. It also takes all the hassle out of making additions and adjustments. Simply change the text, and you’re done. Want to add temporary content for an exhibition? Ta-dah! The algorithm will still make some mistakes from time to time – after all, the programmer no longer knows what the system has learned (or not). But these errors can be corrected manually. But are the voices all top-quality? No, as that requires more money and more patience. But for 99% of museums and their visitors, this is a fantastic development.
List of Services
-
Business success means getting up more than you fall down. The Netherlands is yet again covered in a blanket of snow. Cue chaos in the media and on the streets. The national weather agency issues the highest weather alert code, and everyone’s on their guard. Nobody wants to slip. But I take a slightly different view: I know how much there is to learn from slipping up – figuratively. Although the time between falling and getting back on your feet can be quite painful, these are the moments that provide the most valuable lessons.Business success means getting up more than you fall down.
-
Building inclusive visitor experiences, where to start? At Guide-ID it’s in our DNA to help our clients tell their stories. Audio guides can open up your museum and make it accessible to all, in ways that you may not yet have considered. Here, we’d like to share with you how we can help you become more inclusive, using the options our audio guides have to offer. Let’s start by sharing the first step towards ‘all-inclusive’ storytelling. When creating an audio guide, start by asking yourself these three easy questions: who, what, where?Building inclusive visitor experiences, where to start?
-
Enrich your content with a diversity of perspectives. Connect to your audience by 'speaking their language' in audio tour content. I believe that museums are the mirrors of our society. This is because the collections they display and stories they tell appeal to a diverse audience. When I embarked on my career in the museum sector over 20 years ago, educational services were a hot topic. Museums had begun organizing guided tours and workshops for schools and groups, and placed labels and texts for individual visitors (although these were still often written in technical jargon). This was the point at which museums became even more accessible – you no longer had to be an art expert to understand what an exhibition was about.Enrich your content with a diversity of perspectives. Connect to your audience by 'speaking their language' in audio tour content.
-
The In Flanders Fields Museum comes back to life It certainly felt good to see a sign reading ‘FULLY BOOKED’ outside a museum. The In Flanders Fields Museum (IFFM), like many other Belgian museums, sold out during the Easter holidays. The weather and the Belgian travel ban undoubtedly made a difference. Museums, including the IFFM, remarked that many visitors were people who would not normally visit museums.The In Flanders Fields Museum comes back to life
-
Customer-driven development - How we use co-creation to optimize our products. At Guide-ID, we’re passionate about technology and culture. Combine these two to create the perfect job. Since 2009, our creative team’s passion – and increasing customer collaboration – has driven constant improvements to the Podcatcher platform.Customer-driven development - How we use co-creation to optimize our products.
-
On your marks, get set, go! Yes! We finally seem to have turned the corner. Museums can reopen their doors in increasing numbers of countries. Visitors can barely wait to visit museums once more, and Guide-ID is ready to share stories with them once more. During the pandemic, we worked to make our entire platform easier to use for existing and new customers. In this blog, I will explain why we are truly worthy of the title ‘world’s easiest audio guide’.On your marks, get set, go!