: Denphone Digest :: November 2009 :: Volume 1, Number 8 :
September Issue
In this issue we take a look at an exciting up and coming company called Inferret who specialize is voice and text recognition apps for handsets such as the iPhone. We also have a short how to about displaying twitter feeds on Polycom desk phones, and we introduce an interesting IP phone - a hotel phone from Japanese manufacturer Nakayo.
As ever, if you would like to see something featured in Denphone Digest, feel free to contact us and we will see what we can do for you.
If you are having trouble reading this email version, click to read the web version: http://www.denphone.com/denphone-digest-November-2009.
In this issue:
- Presidents Corner - Huw Williams
- Ferreting out the answers: Natural Language Processing and Speech Recognition with Inferret
- From the IT workbench: Using the Twitter API to display tweets on Office Phones
- Featured products: Nakayo SIP Hotel Phone
- Denphone BCP: Swine Flu: A Checklist for Businesses
- Around the internet
Presidents Corner
The last few months have seen some quite dramatic changes for many companies as the global economy has been getting back on its feet. At Denphone we have been kept busy with a large number of clients pulling the trigger on projects that they had been keeping on the back burner.
We have completed stage two of a major upgrade of our Tokyo data center allowing our clients to enjoy significantly greater SIP and IAX2 trunking capacity while at the same time enjoying the safety of triple redundancy. We have also released version 1.5 of our MicroPBX - now with an even smaller footprint and with support for 10 users - twice what was previously possible.
We are also completing a POP in Yokohama allowing us to offer our clients 045 prefix phone numbers in addition to our existing Tokyo 03 and Osaka 06 services.
Huw R. Williams
President
Denphone K.K.
Ferreting out the answers: Natural Language Processing and Speech Recognition with Inferret
Inferret is a company that is pushing the boundaries of speech recognition and natural language processing. Inferret is currently gearing up to offer speech recognition as a software service to application developers, with a core focus on iPhone and web application developers. While not a VoIP company per se, the areas they are working in border the telephony world in many fascinating ways and offer a plethora of new opportunities for the future. Denphone's Simon Gibson caught up recently with Inferret co-founder and CEO Ed Whittaker for a brief chat about Inferret and the world of speech recognition.
Simon: First of all could you tell us a little about Inferret?
Inferret was incorporated in August of 2007, as a spinout from Tokyo Institute of Technology focusing on natural language processing and speech recognition. At that time I was still a Visiting Researcher at the Tokyo Institute of Technology but it wasn't until April of this year that I left the University to focus full time on Inferret and our new speech recognition service offering for developers. All our applications reside in the cloud, so the users of our products do not have to know too much about how our products work either to use them successfully or to add the extra functionality to their existing applications.
Simon: Can you tell me more about the current product you are working on?
At the same time as developing our cloud-based speech recognition platform for developers, we are also developing our own speech recognition applications for the iPhone, mainly as a showcase of our core technologies. Our first application allows users to easily search Japanese train timetables covering the whole of Japan simply by saying the name of the departure and arrival stations in natural language, so just like asking a human. The software searches for the two most likely matches and returns the timetable information for the requested two stations. This app was released just over a month ago (September 2009) and was the first iPhone app to allow voice searches of Japanese train timetables in this manner. We currently have several thousand active users with many tens of thousands of accesses since then. The overall response from our users has been very positive. Currently we are just offering the Japan train timetable but hope to extend this to other regions and languages in the near future. In fact, our new speech recognition platform will take everything one step further and allow outside developers to do all this themselves.
(Simon: I tested this app and it works well. I said Hiroshima and then Osaka, and it returned the next train between Hiroshima and Osaka. When I tried to say it with a very strong New Zealand accent (Lynn of Tawa, anyone?) it wasn't able to recognise the station names but then I imagine only other Kiwis and perhaps some Australians would have been able to understand what I was saying.)
Simon: What is the status of speech recognition in Japan?
I think compared to the United States and the UK, where speech recognition is already quite mainstream, Japan still has some catching up to do. That said, I believe speech recognition apps will really pick up in Japan in 2010. This is especially true as they are starting to be much more usable and reliable and people here are starting to understand the convenience they offer.
Simon: What was your background? and how did that drive you to where you are today?
My research background has focused on natural language processing and speech recognition and the search capabilities that the combinations of these technologies allow. When we started out we thought we could be the next Google - which in retrospect wasn't a terribly good business plan. We dabbled in many areas around the fields of search, speech recognition and natural language processing, and even social networking. One thing that turned out to be very important for us was the process of talking to customers, getting feedback from them and finding out what they really wanted and were interested in. This has now given us a pretty good idea of what customers want, and what kind of systems we could develop and we now feel we're very much on the right path.
Simon: What other applications have you developed?
Another app we have put together is an improvement on the traditional text-based train timetable search application, although really it is applicable to any text-based vertical search engine. The current app takes 2 station names as input which are then processed using our proprietary algorithms and databases to find the 2 most likely matching stations. This is especially useful for foreigners in Japan - so if you don't know the exact spelling of a station's name you can give it a rough guess and it will still get the correct answer.
A good example of this is a station like the one closest to Denphone - Azabujuban. Easy to write in English, but if you have to break it down into Japanese is it Azabu or Azabuu, Juban or Juuban, one word or two words and is there a hyphen between them? So our system works even if there are several mistakes.
(Simon: I tried this with the following:
azabujvsb -> odska
and the third result was the one I was after - Azabujuban to Osaka. I then tried:
abujukbah -> jotugakga
which quite amazingly returned the stations I was looking for Azabujuban to Jiyugaoka.)
The functionality is similar to the spell check in Microsoft Word or Open Office but also exploits knowledge about the domain and task (in this case station names in Japan). We can also make platform specific adjustments. For example, if you are using the iPhone keyboard there are some common mistakes which our application can learn to correct.
Both speech recognition and natural language processing have to deal with noisy input, albeit different kinds of noise. The pattern recognition approach, which all our applications rely on, uses previously observed patterns of characters and users' mistakes for training. It essentially learns and becomes very robust to such noisy inputs. Clients currently have a great need for this kind of text spell-check and pattern matching functionality, but the way of the future is definitely moving towards complementing such applications with speech recognition as well.
Of course, clients also want to know how such technologies will translate into savings or increased revenue, and the answer is quite simple - providing better user experiences leads to greater levels of user retention and word of mouth referrals. One only has to think about Google - they became the number one search engine by offering the best user experience through reliable search results. Ok, they had a great business model as well which certainly helped. But these kinds of advanced search options allow companies to increase user satisfaction while also being a factor in brand differentiation.
Simon: What have your customers reactions been like?
They have been very positive. We show a demo to a customer and then we see a glimmer in their eyes as they realise how they can apply our services and technologies to their own unique problems. It quickly becomes clear to the customer how they can differentiate their services and leverage our technology to solve the particular problems they are facing.
Simon: I would have thought there would be more resistance to a new service such as yours?
I think the big difference compared to 5 years ago, is that these services actually work really well. We have a lot more data today, much more powerful computers and mobile phones as well as the speeds that 3G internet offers. In the case of speech recognition we also have much better microphones on the handset side. All these advances are exemplified by the iPhone which allows our systems to be multi-modal, complementing typing and pointing with speech-to-text in a much more intuitive and reliable manner. On a device such as the iPhone, users often find it much faster to input data by speech rather than by typing. So I would say all of these factors have actually helped reduce people's resistance to our services.
Simon: What are the potential telephony applications for your services?
As I mentioned we are starting to offer speech recognition as a service. This means giving developers all the tools they need, including client libraries, to quickly and easily add speech recognition functionality to their existing applications. If, for example, you are developing telephony applications such as interactive voice response (IVR) systems then there is certainly a wide range of ways that our services can be applied. We are currently working on a solution for Asterisk to interface directly with our cloud-based speech recognition platform. I hope this is something that Denphone will also take an interest in. Most of the hard computational work is done on the server side - we want to provide as many means as possible to access the server from different platforms and using different programming languages. The idea is to make it really easy for any developer to get up and running right away. The service will work similarly to many existing web services, with a limited number of daily requests provided for development purposes, moving onto a paid service once the projects go live.
Simon: Just before we wrap up, any words of advice for someone looking to start up a company up in Japan?
That depends which business you are thinking of, but for a tech startup my main advice would be to make sure you get enough investment to take you through 2 to 3 years of little to no revenue. Make sure you know as much as possible about your investors before you start - and the fewer of them the better by the way! You should obviously have a business plan but use the feedback from your prospective customers to keep refining your plan. Unless you are lucky you will need about a 2 year window to really get things going. And even then of course nothing is guaranteed - you may get a contract, do all the work, and the client may not end up being able to pay. You need to prepare for all such eventualities by keeping your pipeline of projects as varied and full as possible.
Simon: Thank you for taking the time to talk to us today.
Ed Whittaker has a Masters of Engineering in Electronic Engineering from the University of Nottingham and a Ph.D in Speech Recognition from Cambridge University Engineering Department. Since graduating from Cambridge, he has worked for Compaq, Cambridge Research Labs (Mass.) and Philips Research Laboratory in Germany. He joined the Tokyo Institute of Technology in 2003. In his spare time he enjoys keeping up with technology, and gadgets.
Inferret is looking for potential investors as well as third-party developers interested in integrating Inferret's speech recognition platform into their own applications. For inquiries please contact Inferret - info @ inferret.jp
From the IT workbench: Using the Twitter API to display tweets on Office Phones
Simon Gibson
Twitter was launched in 2006 with the idea that small groups could be kept up to date with what an individual was doing. So for example, if you were walking down the street and saw a cool new pizza place, you could send a short message to all your friends and if they were free, they could come and join you.
At Denphone we are currently working on a presence solution, and while working on that, one thing that popped up as an idea was getting twitter messages to display on the screens of our office phones. With a private group on twitter, it would be possible to use this as a department or company wide broadcast system; especially in conjunction with a BCP system.
The Polycom handsets that we use and recommend, include a number of models that support an xml browser. We have tested the twitter message display on the following models: Polycom Soundpoint 450, 550, 601, and 650. We haven't yet tested this system on Cisco VoIP phones, however it should work in the same way.
Setting up Twitter Message Display
There are three parts to setting up Twitter message display on Polycom phones. First you need to use the Twitter API to draw down the tweets and put them into an XML format that the phones can understand, then you need a web server for the phones to pull the messages from, and finally you need to set up the phones to poll for the messages. Setting up a webserver is a pretty common task, so we wont look at that here - if you need, you can refer to: Ubuntu LAMP Server - Setup Guide with Desktop GUI or for OS X: How to setup Apache, PHP, & MySQL on Mac OS X 10.5 (Leopard).
The Twitter API
The Twitter API provides developers with a simple, easy to work with way to access what is happening on Twitter. Information about the twitter API can be found here: http://apiwiki.twitter.com/. A great number of developers have produced wrappers for interacting with the api in a large number of languages including ruby, python, php and many more. I just wanted to keep things simple so I chose one of the php wrappers. It was created by Ashley from papermashup.com and uses curl, php and xml. You can grab the original code here: http://papermashup.com/using-the-twitter-api/.
I simplified Ashley's code quite a bit - the Polycom phones only support either monochrome, or 2 or 4 bit greyscale images, and don't have much screen space so I didn't want to display avatar pictures.
Here is the hacked down code: http://www.denphone.com/files/code/twitter-polycom.txt.
Polycom Phone Settings
Polycom handsets, being IP phones - with their own processor - are very powerful machines with a huge range of options available to meet just about any possible need. Polycom also offer great resources for developers, and to get twitter displaying on the phones, I used the "Web Application Developer's Guide for the Polycom Soundpoint IP/ Soundstation IP Family (SIP 3.1)" which can be downloaded here.
To set up the phones to receive the twitter feeds you need to edit either the sip.cfg file (normally in the /etc/asterisk folder) or the individual phoneXXX.cfg files. Editing the sip.cfg file means that all phones will use the same feed, editing the individual files means you can assign different groups within an organization to their own specific feed.
In either of the files, add a microbrowser section with mb.idleDisplay.home, in our case this was: mb.idleDisplay.home=http://192.168.1.44/polycom/twitter.php.
Other options you can set include:
- Http proxy - mb.proxy=192.168.1.1:8080
- Home page - mb.main.home=http://www.denphone.com/
- Page refresh - mb.idleDisplay.refresh=10
More commands can be found in the developers guide on pages 2-36 to 2-38. One thing to note regarding page refresh - that sets the number of seconds before the idle page is refreshed - is to be aware of any limitations to the number of API calls you can do per hour or day. Twitter limits api calls to 100 per hour, so setting it to refresh to say every 30 seconds means that the feed will fail to display once you reach the 100 call limit.
Basically any feed - not just twitter - can be supported. So if your users need stock prices, echange rates or even cricket scores showing up on their phones, then that can be quite easily achieved.
Featured product: Nakayo SIP Hotel Phone
Nakayo IP-4N-ST101S SIP Hotel Phone
The Nakayo IP-4N-ST101S is a simple VoIP phone perfect for use in hotel rooms or reception areas where call volume is low and a reliable, simple to use telephone is required. This hotel phone has four programmable one-touch buttons which allow assignment of numbers to be dialled at the push of a button. This means the phone can be easily integrated into a hotel management system so that visitors can extend their stays or order room service at the touch of a button. The phone also has a printable face plate which can be silk screen printed with a company logo as well as with labels for the one-touch buttons.
There is a large misconception many people have regarding VoIP phones and VoIP services - that the quality is not very good. This is a result of people using cheap calling services. With a phone such as the Nakayo hotel phone, and with a properly configured network, the sound quality is as good if not better than with an analog phone.
The Nakayo IP-4N-ST101S SIP Hotel Phone features:
- Printable faceplate
- 4 One-touch dial buttons
- Robust design
- SIP support
- QoS Flag support
We have been trialling this phone in the office and found it easy to set up and use.
Swine Flu: A Checklist for Businesses
Gary Binda
Unlike most Business Contigingency incidents which hit us unexpectedly and need instant action, a pandemic gives us the luxury of time to prepare. Do not let that time be wasted! If you use the next six months to strengthen your pandemic plan you will be ready when the real thing arrives.
Hopefully this article will give you the arguments you need to convince all stake holders in your organization that we are in a lull and that now is not the time to relax.
The World Health Organization (WHO) has said we should remain on alert. The current 'round of activity' might have peaked, WHO official Gregory Hartl said, but that did not mean it was over. 'There is a high possibility that this virus will come back", he said.
Previous pandemics, including the Spanish Flu outbreak of 1918, have been seen to start with a mild strain breaking out in small pockets and followed by the pandemic later in the year. So the chances are that we will see a more extensive outbreak (and possibly a full pandemic) - especially as we move into the colder winter months.
For anyone who has to manage the pandemic planning for their organization, or would like to see some in place if there is none, use the WHO information to stress that we are not out of the woods yet.
What steps should you be taking to ensure you are prepared for a pandemic? The advise below comes from the various Government pandemic planning departments and outlines neatly the high level actions which should be taken.To reduce the impact of these potential problems, businesses will need to ensure that they have a pandemic plan, and I would also add that you should arrange for a test of your pandemic plan as soon as possible.
To be as prepared for further out breaks, organizations should have:
- Identified critical activities that must be maintained and, by implication, what work could be deferred
- Identified the resources needed to deliver these, particularly staff
- Considered both the number of staff and which specialist skills, knowledge or authority are required to ensure continuity of core business areas
- Made available the information required by those staff who might be required to deputize for others
- Put in place arrangements so changes in work priorities can be implemented and resources realigned, in order to maintain critical business activities
- Put in place arrangements to maintain good communications with staff, customers and suppliers
Around the Internet
The big news at the moment concerns Skype's possible plans to opensource development of the Skype platform. This would be a sound response to the threat Skype face from Google voice. It would allow Skype to focus on the termination side of the business (which is where their revenue is generated) while giving something back to the community. And this builds well on the work that Skype has been doing with Asterisk and with Digium to broaden the range of offerings they have and to dig their way deeper into the realm of business services.
Stories Swirling About Skype's Source
November 2nd, 2009 by Justin Ryan
The rumor mill is alive and well in the Open Source world, as demonstrated by wildly spreading speculation about the possibility of an Open Source Linux client from the popular Skype VOIP service.
The commotion began over the weekend with a blog post from a Mandriva user reporting that Skype Technical Support had indicated, then confirmed, that an Open Source Skype client for Linux is in the works. [The post in question is a French-language source, our information regarding it is taken from an English-language summary.]
The news quickly spread, and ultimately resulted in a blog post from Skype developer Stanislav Karchebny (known as "Berkus"), confirming that an Open Source client for Linux is indeed in development. Karchebny declined to comment on the details, but did state that the client "will be a part of larger offering." He spoke of adoption "in the "multicultural" land of Linux distributions" and the promise of rapid advancements - hallmarks of Open Source development. He promised that updates will be forthcoming - Skype's idea of regular updates and the Linux community's expectations, however, do not necessarily sync up.
Some have questioned why the move should be of particular import, given the variety of Linux-compatible VOIP options already available. The most obvious is, fittingly enough, the news itself: Skype will have an Open Source client. Regardless of the market, number of users, or general usefulness, any time the makers of a proprietary product choose to embrace Open Source, that in itself is an important event. Adding allies to our community is as important as adding products to our systems.
Beyond the victory itself, there is the matter of access. There are a number of high quality open VOIP clients to choose from, most of which can communicate with one another out of the box, but only Skype can communicate with Skype. It may be lagging behind in Linux users, but Skype has heavy adoption from users of the market-leading operating system - users on the other side of the wall, so to speak. It's fine to point out the existence of other options - particularly when they are superior, as Open Source software often is - but when the users you're trying to reach aren't reachable, it doesn't do a lot of good. It's rather like being told that you can always mail domestically when all your contacts are abroad.
The move, if it materializes, will likely be of particular interest to business users. More and more businesses, particularly small businesses, are adopting Skype as a way to keep communication costs low - we know from experience. Having an Open Source client that can spread to all Linux distributions will open the door not just for those already using Linux in business, but will strike down one more barrier for those looking to leave their current operating system for Linux. That, like the move in itself, is nothing to be sneezed at.
You can read the original article on the Linux Journal website here: Stories Swirling About Skype's Source.
Japan's 32 Best iPhone Apps (All Available In English)
by Serkan Toto on September 6, 2009
It's not really a secret that Japan is absolutely crazy about cell phones. And even though domestic makers churn out more than 100 different handsets every year (some of which are simply amazing), the iPhone is selling over here. SoftBank Mobile, the country's exclusive iPhone provider, doesn't release official data, but estimates put sales in Japan at well over one million units so far - not bad at all in this hopelessly over-saturated market. In other words, Japan doesn't hate the iPhone, as some blogs suggested in the past. It never did.
The local developer community has noticed and produced a slew of apps aimed at a global audience. What follows is my subjective selection of the 'best' of these made-in-Japan apps, all of which are at least available in English.
We certainly look forward to seeing companies like Inferret being listed in such write ups in the future.
You can read the original article on the Tech Crunch website here: Japan's 32 Best iPhone Apps (All Available In English).
Britain's Oldest Working Computer Roars to Life
Wired's Gadget Lab have an interesting article up that talks about efforts to bring Englands oldest functional computer back to life. Construction began on the "Wolverhampton Instrument for Teaching Computing from Harwell" - also known as the Harwell Computer, and later as the Harwell Dekatron Computer or the Harwell WITCH - back in 1949. It became operational in April 1951. Assembled from components more commonly found in a British telephone exchange, it is a decimal machine with 40 8-digit decatron registers for internal storage. Having been in storage for the last 30 years, it is now being restored to its former glory.
Britain's Oldest Working Computer Roars to Life
The Harwell computer, also known as WITCH, is getting a second lease on life at the National Museum of Computing at Bletchley Park. The machine is the oldest surviving computer whose programs, as well as data, are stored electronically, according to the museum.
The Harwell WITCH is a relay-based machine that used 900 Dekatron gas-filled tubes, each of which could hold a single digit in memory. It has paper tape for both data input and program storage. The computer was used in the design of Britain's first nuclear reactors. (Read more about the computers used at Harwell in the 1940s and 1950s.)
'Its promises for reliability over speed were certainly met ' it was definitely the tortoise in the tortoise and the hare fable,' says Kevin Murrell, a director and trustee of The National Museum of Computing. 'In a race with a human mathematician using a mechanical calculator, the human kept pace for 30 minutes, but then had to retire exhausted as the machine carried on remorselessly. The machine once ran for ten days unattended over a Christmas and New Year holiday period.'
Click on the following link to read the rest of the article: Britain's Oldest Working Computer Roars to Life. Wikipedia also has an article (which we borrowed from) here: WITCH (computer).
For those interested, the picture at the beginning of this months newsletter is from: http://panicbuttonblog.com/2008/09/23/random-funny-phone-man/.
Denphone News
Denphone to exhibit at Call Center/CRM Demo & Conference Tokyo
Denphone is proud to announce that they will be exhibiting at this years Call Center/CRM Demo & Conference Tokyo to be held November 12th and 13th at Sunshine City in Ikebukero.
The Call Center/CRM Demo & Conference Tokyo is Japan's leading tradeshow for Call Center and CRM solutions with vendors exhibiting a wide range of hardware, software and services for the call center and customer center industries.
Denphone will be focusing their SIP and IAX2 trunking solutions, as well as managed voice services. This is a good chance to meet up with a representative from Denphone to find out how telephony related technology is moving forward and what new solutions there are now available to both reduce your company's expenditure while increasing employee effectiveness.
Denphone will be giving away 2 IP phones to people who visit their booth - so visit us to be in to win!
The event will be held at Sunshine City Ikebukuro: (http://www.sunshinecity.co.jp/ (Japanese language only).)
For more information (Japanese only) please see http://www.callcenter-japan.com/.
VoIP & Asterisk Lounge November 11th, 2009
The next VoIP & Asterisk Lounge will be held Thursday, November 11th, from 6pm at Cafe Lolita in Azabujuban, Tokyo. This monthly event is a great chance to meet and network with other Asterisk and VoIP users and developers in the Tokyo region.
- Cost: Free Entrance (drinks are between 500 and 900yen)
- Directions: From Azabujuban Station Exit 7 (Oedo or Namboku Lines),turn right and walk 2 minutes towards Roppongi Hills.
- Alternatively, exit at Roppongi station and walk down the hill towards Azabujuban (10 minute walk). Turn left when you get to Tsutaya. Cafe Lolita is on your left.
We look forward to seeing you there!
Mailing List
If you are not already subscribed to our mail magazine you can do so by sending us a quick message via our contact page.
Mailing List Removal
At Denphone we aren't believers in the idea of spam - we face enough of it on our servers everyday - and are sending this magazine to you in the belief that you will find something in it interesting and of use. If you don't wish to receive a further free magazine from us next quarter, just send us an email with unsubscribe or something of that nature either in the title or body of your email.
Suggest to a Friend
If you think one of your friends or contacts would be interested in subscribing to the Denphone Digest, send us a quick email via our contact page.
About Denphone
Denphone K.K. is Japan's leading provider of open PC based VOIP Telephone PBX systems. Denphone supplies Digium / Asterisk solutions, Cisco, Polycom, Nortel, snom and Grandstream phone and video systems as well as our own bespoke solutions.
Contact Denphone
Denphone is centrally located in Tokyo's Minato Ward in Azabujuban. We can be contacted by telephone on 03-4550-1405, via this contact page or by reply to the address this magazine was sent from.
Our postal address is: #402 Azabu Nagasaka Bd, 1-4-8 Azabujuban, Minato-ku, Tokyo 106-0045 Japan.
