Voice User Interface (VUI) has become one of the most natural and intuitive methods of human-machine interaction. Today, we already use it to control cars, smartphones, and numerous connected home devices. We even communicate with businesses such as banks or insurance companies via self-service voice applications, without using touch-tones (DTMF). Take a look at our previous posts on Connected Customers and Contact Centers where we cover these topics in more detail.
In fact, there are several reasons why voice UI is so cool:
All these topics are really interesting and we will cover them one by one in future blog posts.
Here, I’d like to concentrate on a more general use case, when a system takes natural language as input, processes it, creates some business logic, and properly responds with a natural output. So it looks more like a dialogue or conversation with a machine, which ends with a specific business transaction being performed, e.g. transferring money, ordering pizza or making a medical appointment. The diagram below illustrates the simplified architecture of such a system:
Anna wrote a few words about Lekta NLP in our first ever blog post; essentially, Lekta is an advanced Spoken Dialogue Framework that allows the creation of conversational voice interfaces for business applications. Imagine an automatic system for making an appointment with a dentist, ordering a takeaway or automating banking customer services. We won’t go too deeply into discussing NLP as such just now, rather we will concentrate on Lekta’s interface from the user’s perspective.
One possible model is based on receiving the output from the speech recognizer (ASR – automated speech recognition) and then responding through the speech synthesizer (TTS – text-to-speech). Basically, ASR takes the acoustic signal as an input and tries to determine which words were actually spoken. The output typically consists of a word graph – a lattice made up of word hypotheses.
In a future post, we will show exactly how Lekta benefits from using such a lattice and can even help to improve the quality of the speech recognizer itself. Here, we omit the communication details, whether it’s a phone call or a mobile app voice interaction.
Actually, Ratel (Contactis Group’s omnichannel business communications operator) fills in the missing piece by providing feature-rich, context-based communication allowing customers to connect to businesses in the most natural and intuitive way. But that’s another topic entirely.
For now, let’s say that the ASR module returns text results, each result with a certain level of confidence. Lekta then takes this data and extracts a meaning representation (NLU – natural language understanding), which is used by the Dialog Manager (DM) responsible for conversation management and business logic integration. The output from the DM, which is a non-linguistic meaning representation, is then taken to the NLG (natural language generation) which converts it into natural language. The final part of the whole process is produced by the TTS module, which converts the natural language into speech. We will cover each step in more detail in future posts.
The obvious question is this: what if Lekta receives the wrong speech recognition results from the ASR? For instance, Barcelona and Pampeluna could sound very similar in Spanish. Well, here we can, in fact, have a couple of options. The first is based on the business logic – let’s say a client wants to book a flight on a specific date. Lekta can check with the database to confirm if there are flights to Pampeluna on that day, and if there aren’t any, it will be assumed that the client meant Barcelona. However, if there are flights to both cities on the same day, and we know that these names often cause a recognition problem, the system could confirm if the customer requested exactly that particular city (using a “yes-no” question). This may worsen the user experience a little but at least we could proceed with their request, which in this case is more important.
In general, Lekta tries to solve these kinds of problems by controlling the ASR with so-called expectations. Let’s consider an automated medical appointment system, where, at a certain moment, the system asks for the ID of a caller. In this case, Lekta can inform the ASR that it expects digits by providing the more specific (smaller) grammar. In the end, this improves the overall speed and quality of speech recognition.
An important thing about Lekta is that it is language-agnostic and completely independent from the ASR/TTS, so any vendor can be used. It could be more cost effective if a business has already been using an ASR/TTS engine, or uses solutions developed by an affiliated company, which in the case of Lekta is Techmo, a company with some of the best voice technologies in Europe on offer.
As we mentioned at the beginning of this post, our voice contains more than just words. There are solutions available that can detect emotional state, age or gender with a certain level of confidence. Techmo’s solutions can be used for this as well.
According to “Gender recognition from vocal source” research, the male voice recognition probability is found to be 94.7%, and the female voice recognition probability is 95.9%. This is very important for languages with a grammatical gender like Polish or Spanish, and it mostly affects the NLG module.
The emotional state (like joy, sadness, anger, fear, surprise, or a neutral state) in a voice channel is a harder thing to determine. According to various reports, the efficiency is around 45% in the case of male voices and in the case of female voices, it’s around 48%. Lekta can be configured to adjust the dialog strategy depending on the caller’s emotional state. For example, if the customer is detected to be angry or rude, Lekta can transfer the call to a live agent.
Also, Lekta can switch the dialog strategy depending on the age of a caller, for example, by making it more informal while talking to younger customers. All these dynamic parameters (age, gender, emotional state, etc.) can be used by Lekta in order to improve the overall user experience. It’s, therefore, quite difficult to show all the powers of Lekta in one article… which has become quite lengthy with my musing at Lekta’s possibilities! I do hope you enjoyed it though :).
To summarize, in this article I’ve tried to give you a short overview of how Lekta is available via voice interface and what additional features it can leverage. With this in mind, I’d also like to start a series of blog posts in which we are going to cover the details of Lekta NLP.
Today, we as a society feel more and more comfortable with hands-free, non-visual interactions. Voice interfaces will definitely continue extending into other areas of our lives and activities. And thus, so will Lekta.
Before we go into why it’s worth investing in NLP from a company’s point of view, let’s take a look at whether all this artificial intelligence talk could be just a passing trend that your business can do without. One way to think about it: If the market is growing, there must be something in it.
So how does the AI/NLP market look? Well, it’s a little complicated to define what exactly constitutes artificial intelligence but if you think of the all-encompassing robots and artificial intelligence market, like Bank of America Merrill Lynch did, you can be looking at a market worth $70bn by 2020 for just the AI part of it. WOW, right?
Now, according to Tractica, natural language processing is “emerging as one of the most highly utilized technologies in the broader field of AI”. This is due mostly to the increasingly recognized value of data and the fact that a lot of it comes from naturally spoken and written words. Because a lot of data is simply human.
Natural language processing is already used to some extent in healthcare, e-commerce, and IT and telecom industries. Those are also the NLP market segments to grow the most over the next few years.
The overall NLP market size is predicted to arrive at a whopping $16.07bln by 2021, at a Compound Annual Growth Rate of 16.1%. This will be caused mainly by increasing demand for better customer experience, as well as increasing usage of smart devices. The fastest market growth will be experienced in Asia and North America.
In that prediction, a very broad definition of NLP is used, and it includes information retrieval, information extraction, automatic summarization, machine translation and dialogue systems. So, it can mean anything from a virtual assistant to tools for extracting data from huge amounts of spoken and written words, numbers, phrases and sentences.
At Lekta, we chose to concentrate on conversational interfaces and just that has a whole lot of usage possibilities. But obviously, since Lekta is a framework that is not rigidly defined, it can have other applications as well. And we plan to enable developers to use Lekta to create all sorts of amazing things in the near future.
But let’s get back to the topic at hand. Natural language processing is a great technology for automating human tasks without losing the human touch. And yes, that also means that people who did those jobs will have to move on to doing something else. It isn’t necessarily a bad thing, though.
As one Oxford study predicts, “low-skill workers will reallocate to tasks that are non-susceptible to computerisation – i.e., tasks requiring creative and social intelligence. For workers to win the race, however, they will have to acquire creative and social skills.”
We’ll cover the topic of NLP’s influence on the future of employment in one of our future posts, so please do let me know your thoughts on the topic, in the comments section or in a direct e-mail!
Future and Emerging Trends in Language Technologies conference (FETLT 2016), which took place in Seville between 30th of November and 2nd of December, brought together leading researchers, academics and industry representatives for an intense 3-days interactive event.
Co-organized by our CTO, José F. Quesada, and proudly sponsored by Lekta, FETLT’s strategic objectives were to facilitate dynamics between research groups, with special attention to Machine Learning and Big Data. It was clearly one of the most interesting Language Technologies events of the year.
José will write more about the conference and the leading research and industry trends that were discussed there. His article will appear soon right here, on our blog, so make sure to stay tuned! Until then, we would like to share with you this storify compilation, bringing together some of the best moments of the first day of FETL 2016.
Not everyone feels confident that they are getting the best possible help when they call a contact center for assistance. This skepticism often extends to the technology being used when a customer calls with a question. This is important since the technology that the person handling the call can determine how well they do their jobs as well as the kind and amount of information they have about the caller. Technology that provides context about the customer is still a rarity.
Let’s take a look at how contact centers have changed over the years and the technology, information and tools they have put in the hands of employees.
Not so long ago, contact centers weren’t that different from a secretary’s office. Agents working there had a telephone and email. Some of them had an IVR system that could be programmed to route certain calls to certain agents.
It’s safe to assume that agents had very little information about callers – who they were or why they were calling. They had to find out everything during the course of the call, which of course made it last much longer than it had to.
Today, contact centers have more advanced technology that lets them significantly raise the level of customer service they deliver. Apart from telephones, text messages, email and IVR there are chat capabilities and basic bots that can take care of simple questions or set up appointments.
Agents in call centers get help from ACD (automatic call distribution), IVR (automatic voice service connections) and CTI (integration of telecommunications and information technology). These three tech solutions allow calls to be connected to specific agents thanks to ACD, basic verification of the nature of the call with IVR and quick verification of the caller with CTI.
In addition to these tools, agents also have access to video connections that significantly improve service, especially in IT. The ability to see the caller on a video screen makes setting up the parameters of the situation and solving problems much easier.
Some technologies of tomorrow can be found today in certain companies even though not all of them see the full potential of those technologies yet. It’s worth noting though that even the most cutting edge technology has its pluses.
Imagine a situation when you call your bank and you hear “Welcome, how can I help you?” It’s just like when you walk into the local branch, except… you’re not talking to a human. It’s an advanced information system that is able to have a conversation with you just like the friendly agent in the bank would.
The advantages of such a system are obvious:
The Lekta NLP system is making its debut. It implements the logic of leading dialogue and easily adapts to the specific topic of a conversation and takes the conversation in the right direction. Callers have control over the conversation – Lekta just shares information or asks for necessary details.
Lekta can reliably identify problems and deliver relevant information or direct the conversation to the right person along with all the data gathered from the caller.
It may sound like science fiction but this is simply very advanced technology that makes it possible to talk with machines in a conversation that’s no different than a chat between two people. Lekta is the dialogue interface of the future and is available today.
Implementing new technologies often causes anxiety among employees since it raises questions about their future. But not every tech solution means reducing staff. More and more systems are being created to support and help the work of employees and that’s the case with Lekta.
The system is able to handle about 80% of the conversations that usually go to call center agents. From a business point of view, this is a huge help and takes small matters out of the hands of agents, letting them concentrate on more complex matters and customer issues.
Lekta frees up the time of not only employees of call centers but the management team as well. It doesn’t require a hiring process or training and it works all day, every day. It also offers continuous insight into the course of any conversation and makes it possible to optimize offers that are better matched to the needs and expectations of customers.
These features make it worth trusting this technology and integrating it into the customer relations in your business. After all, if you’re not moving forward, you’re moving back.
Feel free to contact us if you want to talk about the Lekta.
Alex Waibel, from Carnegie Mellon University and Karlsruhe Institute of Technology, raised this point during his speech after receiving the META Prize at the recent META-FORUM event held in Lisbon on 4/5 July 2016. Perhaps you could consider any of the multiple other languages spoken in Europe.
By the way, have you ever thought about how many languages, or dialects, are spoken world-wide? Although there are some 7,000 languages registered, the list of the top 25 languages only represent around 50% of the world population. Curiously enough, some publications mention that there are 46 languages that have just a single speaker.
And what about Europe? Well, in his presentation about the digital vitality of European language, András Kornai from the Hungarian Academy of Sciences mentioned a list of 283 European languages and dialects.
By the way, the difference between what’s a language and what’s a dialect can sometimes be very diffuse. Don’t forget the famous quote on this point: “A language is a dialect with an army and navy”. But even with 283, Europe is not the richest linguistic area in the world. For example, more than 850 languages are spoken in Papua New Guinea alone, a country with less than 8 million people.
But in any case, language is currently a major barrier for the economic and social development of Europe. This is the key motto of the Multilingual Single Digital Market (MSDM). Georg Rehm, from DFKI, current META-NET General Secretary, summarized this challenge with the sentence “Don’t understand, won’t buy” during his presentation of a new version (0.9) of The Strategic Agenda for the MDSM.
However, I would like to highlight two key, inspiring ideas mentioned during the two intense working days in Lisbon.
Ryan McDonald from Google focused on Multilingual Europe as a Challenge for Language Technologies.
The key points he presented were quite strong and very relevant for this community:
António Branco, Principal Researcher of one of the most prominent EU-funded projects on Machine Translation (qtleap), used an insightful idea for motivation in his talk.
In the past, with the advent of PCs, companies reached out to their customers with websites. Currently, with the consolidation of smartphones, the strategy for reaching clients is dominated by the use of mobile apps.
Recently, a CEO of a large social network at an annual conference proposed that, in the future, companies will reach their clients using chatbots.
Summing up, Multilinguality, Mobile and Conversational Interfaces will play a critical role in the immediate future. It’s important to create solutions that won’t be limited to English or any other single language.
Fortunately, Lekta has been designed to take into account all these challenges, and now we are ready to put it into action. Stay tuned!
Pictures and graphics:
Artificial intelligence is taking over the world whether we want it or not, so we can either make it work for us or against us. I choose the former. But how? That’s one of the things we talked about with some fellow startuppers last week.
It’s good to experience the startup community firsthand from time to time. It helps you keep your finger on the pulse much more effectively than just gathering data online or talking to people on Facebook and Twitter. That’s exactly why we decided to go to the SaaS Meetup, to see what the perceived trends in the startup world are, and to talk to some founders to find out whether these trends actually mean something. We also wanted to introduce some of our ideas and get feedback on how to best develop, launch, and promote our project.
So, we got into a few discussions on AI, NLP, machine learning bots taking over the world and all that. But… before I go on to talking about the outcomes, maybe I should start by telling you what it is we’re doing at Lekta :).
Well, in a nutshell, we’re doing some really awesome stuff. I’m not saying that simply because it’s my job to put Lekta in the best light possible but because I’m honestly and extremely excited about the possibilities that lie ahead of us. And by us, I don’t just mean the Lekta team, I mean the entire world; the world of everything connected: connected customers, connected devices, connected businesses.
But anyway, I’m starting to babble and you probably just want to finally find out what Lekta is. Right?
Lekta is an advanced spoken and written Dialogue System Framework. It redefines the way people communicate with businesses. Lekta’s cutting edge technology can automatically manage millions of conversations with customers, users, and devices.
And what exactly does that mean? It basically means that you can use Lekta as a voice (and also text) interface for anything you want. It can be a 24/7 virtual agent in a contact center, e-commerce store or a doctor’s office. It can add voice control to any app. It can enable your IoT devices to have a real conversation with you. It can help you to easily connect apps to each other, apps to devices, and more.
I call it “Siri on steroids”, but Lekta is so much more than that. I’m not going to go into too many technical details because I’m not the one who should do it, the creator of Lekta, Jose Quesada, and our Lead Developer, Daniel Slavetskiy, are way more qualified to do that. And don’t worry, they will. Soon. On this blog.
In the meantime, let me go back to our SaaS Meetup discussions.
We mainly discussed AI and NLP and specifically tried to answer the question whether the two actually make our lives easier. Do people prefer touchscreens and clicking a couple of buttons instead of using voice commands? And do they prefer talking to a human instead of a virtual assistant? Well, the opinions vary but we did come to some conclusions*:
So those are the main things we managed to discuss between keynotes and lunch :).
The keynotes though! The speakers only assured us in thinking that we’re right in the eye of the AI storm. The predictions are that basically everything will be AI-enabled sooner or later. Starting with healthcare, marketing and business intelligence.
According to Nick Franklin‘s (CEO of ChartMogul) keynote, AI will also be crucial in customer service, sales, and bookkeeping. The UI paradigm also shifts toward more natural language in both text and voice communication.
Since Lekta is all about AI and NLP, I’d say we have a great chance of becoming part of something big – bigger than just a passing trend and temporary hype. AI is here to stay, so let’s use its full potential to make our lives… even more enjoyable!
*Remember, these are just conclusions from a bunch of startuppers, based on what they heard, read, saw, and experienced – so not exactly a sample representative of our entire society. But still, I think we managed to touch on some important issues that can be a base for further discussion. So… is there anything AI/NLP-related that you would like to discuss?