Beginners Guide to Voice Services In the Age of Digital Assistants

Leveraging your voice to initiate a command, start a service or even change the channel has been around for years. I remember in my grade school days hearing the voice of my parents or grandparents to fetch them something from the other room, change the channel on the television or even just to be quiet. These days, kids have a lot of distractions, from tablets to noise canceling headphones, rendering those ‘old school’ personal assistants no longer available.

All jokes aside, digital assistants and voice driven interactions are becoming commonplace as voice services increasingly improve. BlueFletch has been fortunate enough to work with clients across an array of industry verticals to explore how voice services will impact their organizations. We’ve helped our clients leverage voice services for more impactful engagement with their customers, allowing them to engage customers in new ways and capturing metadata that would be lost during a normal human interaction. Other clients are increasing the efficiency of their workforce by adding voice services in order to allow a worker to be hands free, keeping attention on critical actions and creating a safer work environment.

A (Recent) History of Voice Services

In recent years, we are yelling less at kids and more at Alexa, Bixby, Cortana, Google and Siri. Every major tech company is working on its own digital assistant that is powered by a set of voice services.

      • Apple released Siri in 2011 and now Siri is apart of most of Apple’s operating systems (i.e. iOS, watchOS, macOS and tvOS)
      • Amazon Alexa was made popular by the Amazon Echo and the Amazon Echo Dot. Fun fact, the name Alexa was chosen due to the fact that it has a hard consonant with the X and therefore could be recognized with higher precision.
      • Microsoft lifted its character from the Halo video game franchise to launch their intelligent personal assistant Cortana.
      • Google Assistant was unveiled just last year. Different from Google Now, the Google Assistant can engage in two-way conversations.

This year has been the year of the voice for BlueFletch. We have been a part of many workshops and brainstorming sessions where voice is the centerpiece of the User’s experience. For those new to the space, I wanted to talk about the three technologies that are key to bringing these voice experiences to life.

Three Parts of Voice Interaction, An Explanation

voice recognition

Voice/Speech Processing

The first part of recognition is to efficiently and cleanly capture one’s voice. Overcoming barriers like speaking style, background noise and tones. Advancements in sound processing, thanks to more powerful devices, has allowed for tremendous improvements in sound processing. Most modern devices today have at least two microphones which allows for real time signal processing and noise canceling.

It is important to first capture a clean audio sample so that it can be processed with a higher degree of accuracy. Also, with the advancement of network speed voice processing can happen in real time. Meaning that as you record, you are sending your voice data directly to the server, which translates into faster interactions with systems.

speech recognitionVoice/Speech Recognition

Speech recognition has been around for quite some time. When we speak our voices produce sound waves. These sound waves are made up from the tones and sounds that are a part of the language we are speaking. The inflections in our voices, e.g. the way you use your bottom lip and tongue to pronounce the word ‘flip’ have patterns that are used to understand what you are saying.

Deep learning has finally made speech recognition accurate enough to be useful in broad everyday scenarios. Combining these speech patterns with patterns in dialect and grammar rules feed algorithms that continue to learn and improve the accuracy of transcriptions. In short, our voices or speech are converted into text/words.  

natural language processing

Natural Language Services

Natural Language Processing or NLP is a way for computers to analyze, understand, and derive meaning from human language in a smart and useful way. The words that are captured as part of the transcription service need to be understood by the application.  To do that, the words are broken down into two parts; intents and entities.

        • Intents are mean to define the purpose of the phase.
        • Entities provide context. If intents are the ‘what’ of the phrase the entities are the ‘who’ and some times ‘where’.

A simple command such as, “Tell me about today’s weather” is separated into intents and entities. The intent is weather. The entities are today and current location. With this information the application understands to provide today’s weather information at a specific location.

This seems easy but there are a lot of power algorithms that are able to quickly process this information. These algorithms and the data that is available are the differentiators between the available platforms.  When you combine the processing/capture, recognition and natural language of one’s voice things can start to happen.

Hopefully without being too technical I was able to explain what is happening behind the scenes when you are yelling at your favorite voice assistant.

Always On Home Security

google fiber home security

With the impending arrival of Google Fiber in my neighborhood, I can’t contain how happy I am to finally have an alternative to Xfinity. I am not sure why I am forced to have a landline when I do not even own a phone, but that is a separate blog within itself. One service that Xfinity offers is their Xfinity Home service for security and remote home management features. Since a comparable service is not available with Google I see this as an opportunity to put together a solution leveraging a few technologies that I have been wanting to dive into.

  • Machine Learning
  • Big Data
  • Digital Fingerprinting / Identification

As most of you are aware by now, if I can tinker around and create something myself, I am going to try. While working on a couple of retail based POC’s for client projects at BlueFletch I got the idea for creating a home security system. The source of my inspiration were these two proof of concepts:

  1. Tracking and identifying customers in a retail location from the devices and/or applications they would have.
  2. A device that could manage other smaller beacons in a retail location.

My ‘aha’ moment came when I realized I could use these same techniques, combined with machine learning, to detect when devices (and, therefore, people) are in and around my home. And if a creeper goes low tech and leaves their devices at home, I’ve got a plan for that scenario as well! With listening and video models I can track and record any unwanted presence.

How This Works

Step 1: By strategically placing devices and IP cameras around my home and property I can monitor and record activity. The information that I gather will be processed and stored in the cloud. Since I am a glutton for punishment and recently spent a lot of time with Microsoft products, I will be leveraging Microsoft’s Azure cloud services.

Initially the devices will listen for signals being broadcast by other devices. This continuous stream of information will flow to and be stored in the cloud for me to manually process and determine if there are any patterns.

Step 2: Once I have confidence in the data that I am receiving I will build my first model to process the stream of data.

My goal is to train my model with a simple set of binary (yes/no) questions. When a new ‘thing’ is detected the system will ask me via text messaging if this thing is known or unknown. From there I can start to dig deeper and categorize ‘things’ I detect.

Step 3: IP cameras will always be recording and can take requests for timestamped images or video. Only data from a requested period of time will be stored. E.g. When a thing is detected, send along the visuals for that moment in time. This will provide me additional context so that hopefully I can visually see what has been detected digitally. In later versions I could even leverage cognitive services to detect people or things in the visuals that are captured.

The goal is simple. Can I detect if someone is at my home that probably should not be and if so then let me know so that I can do something about it. Smart, simple, affordable home security.

How to test the efficacy of your Omni-Channel – BlueFletch Uses Optiko to Power Retail’s Buy Online, Pickup In-Store

The “Buy Online Pickup In Store” offering has become a popular addition to most retailer’s omni-channel strategy over the last few years. Flexible fulfillment programs that integrate all three sales channels – online, in-store and mobile apps – can reduce shipping costs for customers and increase overall sales by drawing more shoppers into the store. BOPIS improves customer satisfaction and allows traditional brick-and-mortar retailers to more effectively compete with major online stores.

In an age of Amazon Now/Echo, Alibaba, Mobile Payments and other disruptive retail technologies, customers are demanding and expecting more from brick-and-mortar retailers. Retailers must acknowledge these expectations or risk losing out to the competition. Today’s savvy and busy shoppers want to save two things: time and money. BOPIS as part of a bigger omni-channel strategy can deliver on both.

Strategic advantage of well implementing BOPIS include:

  • More unplanned purchases when shoppers visit the store (40% vs only 25%).
  • Faster delivery.
  • Connecting customer data from online to offline for insights down the road.
  • Larger basket sizes.
  • Higher conversion rates.
  • Sometimes it’s more convenient than waiting for the item to be delivered.
  • Save on shipping costs.
  • Shorter overall time to receipt of an order compared to ordering online.
  • Price matching now ensures the most competitive price.

Over the last 8 years, we have had the opportunity to implement the mobile applications for a large number of retail BOPIS solutions. One of the key differentiators we have found in successful implementation is to incorporate analytics to measure the experience. We have done this multiple ways, from building bespoke dashboards to customizing Splunk reports. Recently, more retailers have been leveraging our mobile analytics offering, Optiko, to provide this competitive advantage. Access to actionable information from Optiko analytics allows our clients to gain insights so that applications and associate training can be improved based on actual data – not causal feedback. Gaining insights based on actionable data allow our clients to measure their return on mobile technology investments and identify where to invest for future improvements.

Read More

BlueFletch Featured on TAG Radio

BlueFletch, TAG Radio, Richard Makerson

BlueFletch Managing Partner, Richard Makerson, is featured on TAG Radio’s Tech Talk.

Today, enterprise mobility is a strategic component of every business. Frank Baia and Richard Makerson discuss how BlueFletch has delivered innovative next gen mobile solutions that improve efficiency and provide productivity improvements and competitive advantage for our clients. Learn how BlueFletch leverages a decade of experience and innate creativity to design custom mobile solutions specifically tailored to our clients individual needs.

A love of learning, a determination to constantly evolve, and the ability to find comfort in the unknown make Richard and the team at BlueFletch leaders in enterprise mobility.

BlueFletch featured on TAG Radio’s Tech Talk


BlueFletch Managing Partner, Richard Makerson, is featured on TAG Radio’s Tech Talk.

Today, enterprise mobility is a strategic component of every business. Frank Baia and Richard Makerson discuss how BlueFletch consistently delivers innovative next gen mobile solutions that improve efficiency and provide productivity improvements and competitive advantage for our clients. Learn how BlueFletch leverages a decade of experience and innate creativity to design custom mobile solutions specifically tailored to our clients individual needs.

A love of learning, a determination to constantly evolve, and the ability to find comfort in the unknown make Richard and the team at BlueFletch leaders in enterprise mobility.


Listen here

Need a mobile solution? If so, will any solution do?

What do I wear? What’s for lunch? Should I buy a new car or a used car?

Making decisions is a normal process. We do it instinctively, day in and day out. And yet, some decisions are more important than others. For the enterprise, the build-versus-buy decision can be a challenging one. Determining whether to invest in long term efforts or chose a more conservative (i.e. less expensive and short term) approach is not to be taken lightly.


When deciding to implement a mobile strategy, will anything do?

First, you must pinpoint what is important to your organization:

  • Reducing overtime with efficiency gains?
  • Capturing additional information to provide the business with actionable data?
  • Access to data in the field?

No matter the strategy, at some point the decision will be made to pull a solution off-the-shelf or build something custom. Not all problems are created equal and neither are budgets for that matter.


Read More…

Finally received my Amazon Echo (echo, echo, echo)

In my previous article 2015 IOT Purchases So Far , I shared my 2015 IOT purchases (Amazon Echo, Lockitron Bolt, LUNA). My Amazon Echo is finally here after spending 6 months on Amazon’s self-imposed wait list.Screenshot 2015-06-22 11.01.35

Background on Amazon Echo

The Amazon Echo is a connected speaker that acts as a personal assistant. You wake up the Echo by calling it’s name  – Amazon or Alexa; and then call out a command or ask a question. The Echo is connected to Amazon’s cloud and my prime account so it is very easy to order previous items or play music from Prime Music. And Amazon is consistently rolling out new features and integrations.

Initial Thoughts

The device is a lot smaller in person than I thought it would be. Setup was very easy and quick. I clicked through a few setup screens with the AmazonEcho App and Alexa was ready. Honestly, I am having a lot of fun just being silly with the Echo.

Integration with connected home devices, such as the WeMo lights in my backyard, was super simple. I pressed the discovery button and, after 15 seconds, Alexa said she found 2 WeMo lights. I can now ask her to turn on/off the backyard lights.

Another feature that plays nicely with how I work is the ability to play news, information and music. Alexa will shuffle playlists from Prime Music and play news from sources including local radio stations, NPR, ESPN and TuneIn. I love having background noise when I am working so I find myself using headphones a lot less around the house. The speaker is ‘Bose’ like, the sound fills the room and the quality is nice. I almost wish I could stream Tidal hi-fi to see if the Echo’s speaker system could keep up.

I have not used Alexa to add items to my to-do list or create reminders, but I have made a few impulse purchases from Amazon Prime. The ability to shout a quick command and confirm when Alexa ask me if I am ready to purchase is addictive.

For a lower barrier of access, Amazon would have to read my thoughts or just assume I need more coconut water, which is probably coming in in a few months. Or as part of prime membership, perhaps someone will come out to my house every week, make a grocery run and restock my house while I am at work.

What’s Next

Amazon has an Alexa AppKit and I have applied to participate in the limited beta. I am hoping to develop some custom hooks and create more scenarios that are not publicly available yet. (e.g. ‘Alexa, it’s time to go to bed’ locks back door, turns alarm on, lights off, trigger’s Nest thermostat, etc.)
I am enjoying the device and I am excited to see how Amazon continues to develop it. I may be over stepping a bit but I think, at least for me, this device could mute potential gains Apple’s HomeKit would have in my house.

First Month with the Apple Watch

Following up on my ‘What Time is It!?!’ blog post, I am finally ready to write about my Apple Watch. I’ve had it for about a month – long enough to share my early thoughts.

RMwatchI purchased the 42mm Stainless Steel case with the Black Sport Band, which will set you back $599.00. I really wanted the black stainless steel version but it was only available with the Steel Link Bracelet, which added another $500 to the already high price. The only difference in the Sport version and the Watch is that the Watch has a different metal for the case and the glass is sapphire instead of glass.

The setup process is very easy and Apple-like. Out of the box you will receive notifications, phone calls and, if you elect to install 3rd party applications, you will get notifications from them as well.



Notifications are a major reason why someone would want the Apple Watch in the first place. Notifications appear much like they do on an iPhone with the ability to be managed individually.

fitnessOne of the things that I loved about my Fitbit was it’s ability to accurately track my Fitness. The Apple Watch does a great job of tracking different fitness activities while also capturing heart rate too. Personally, I really like getting credit and awards for meeting my fitness goals. Knowing that at some point I can show off how constant I am adds fuel to my motivation. However, one thing that is starting to get old is having my watch tell me that I have been sitting too long and need to stand up for a few minutes. I guess I am not ready for machines/computers to start telling what to do just yet.

heartCommunication also plays a significant role in the user experience of the Apple Watch. Receiving my notifications for text and phone calls when I am away from my phone means that I can properly screen my calls without having to sprint across the room. But the fact that if someone important is trying to reach me I can speak Dick Tracy-style on a phone call or have Siri dictate a message for me is pretty handy.

One thing Apple wanted to do was add another level of simple but useful communication (probably as a differentiator). I can tap my watch and that will send a tap to someone else’s watch, send animated emojis, send my own heartbeat and even send simple drawings. I did not think I would like the new communication types, but I find that my wife and I use them quite a bit.

One of the less talked about features is that the Apple Watch has 2gigs of storage for music and can be paired to a BlueTooth headset. Keeping with the spirit of an iPod, it is ideal for working out, walking or jogging.


  • Stylish
  • Precise (Touch Interface and Haptic Feedback)
  • Easy Integration


  • Expensive. I bought the stainless steel 42mm version and could have easily bought a new iPad Air 2.
  • Battery life is not ideal. One solid day of normal use

Screenshot 2015-05-27 09.05.04

My Verdict:

I like it and I am pleasantly surprised. I was honestly prepared to have wasted my money on a first version Apple product. I know in true Apple fashion there will be a slightly better one next year and I will convince myself that being first was cooler than having the latest version. However, I am already over one negative in the fact that I have already purchased the device and if a 3rd party band can extend the life of the battery then I would not see any negative for purchase.

An Innovative Idea for Transportation and Logisitics

Years ago when I worked at Accenture, I participated in a innovation contest sponsored by the United States Postal Service (USPS) account that I was on. The goal was to cultivate innovative ideas that USPS could leverage (or Accenture could use to sell additional work).

Looking back at that competition and thinking about my idea, it is still pretty valid. With the advancements in wireless, mobile and IoT, I would like to revisit and update my pitch.


After graduating from Morehouse College, I started a transportation company. It would be considered a Mom & Pop operation. The data at the time had some eye popping numbers.

In Transportation & Logistics:

  • 90%+ of the companies are 30 trucks or less (Mom & Pop)
  • that would be approximately 500k+ companies
  • most of the technology that supports that industry is expensive and usually is targeted towards larger enterprises.
  • at that time there were a lot of copying, faxing and using excel spreadsheets to provide analytics



Riding the Wave

TIDAL’s streaming music service has been in the news lately. Some are not aware that the Norway based service launched in 2010. Most of us in the US were left feeling awkward by the star-studded press conference led by Jay-Z.

To date, I have not found a compelling reason to pay for a music streaming service. Somehow I have strung together a nice run of winning iTunes gift cards at hackathons and receiving some as gifts. With TIDAL in the news, I figured this would prove a great time to kick the tires and provide my initial thoughts after a few weeks.


High Fidelity vs. Normal Streaming

Can you tell the difference? Yes
Do you care? Probably not
Why would someone spend 2x for high fidelity? If you are an audiophile and care about the details in music that 99% of people just ignore. In the grand scheme of things, the extra $10 a month is a lot cheaper than the $500+ earbuds assembled by Buddhist Monks that you recently purchased. Just my opinion.

Desktop Application/Web Interface

Where is the desktop application?!? Currently it is under maintenance according to the FAQ section. I spend a lot of time at my computer between writing code, answer emails and researching solutions to problems  and a desktop application that leverages the keyboard controls of the Mac or had global hot keys would be greatly appreciated. There are many times when I am at my desk and someone will come over to ask me a question. Having to hunt around for the tab that TIDAL is on and pause the song is getting old.
I wish there was a History View so that I did not have to add songs to a playlist. I have never created a playlist, I do not know why but I just don’t. Having a history view would allow me to start my day the same way – look at a moment of time and reflect on what mood I was in.
Although, I refuse to make a playlist TIDAL has me covered with lots of curated content.
  • You can listen by Genre (Pop, Rock, RnB, Alternative, etc), which is great for me.
  • TIDAL also has curated playlists based on your mood or state. So if you are relaxed, ready to party, focused or having dinner , there is a playlist for you.
  • They also do a good job of allowing trending music (TIDAL Rising) to rise to the top and showcasing what’s new.

 Mobile iOS & Android

Both Apps are solid and provide the same functionality that is available on the web. As a mobile developer I am pleased with the quality and usability of the application. One of the handy features is that there is an offline mode. This is important if you are going to offer high fidelity and reduce cellular bandwidth when not on wifi.
TIDAL also supports integration with a number of additional products, just to name a few:
  • Sonos
  • Bluesound
  • Linn
One thing that I think would be cool is to have a party or DJ mode where non-subscribers could login and queue up tracks the subscriber is playing.

Videos & Exclusive Content

Other than the High Fidelity differentiator, exclusive content is the other appeal that the star studded new investors in TIDAL will offer. TIDAL only (or at least first) videos, albums and songs are another feature that TIDAL is using to win market share in the music streaming business. Jay-Z is actually live streaming a concert on May 13th for TIDAL subscribers.
Having access to a number of videos is an added plus, although I rarely use this feature. I do find myself watching a video or two that looks interesting on the main page.
All in all my time with TIDAL has been a pleasant experience. The search functionality could be a bit more friendlier. Currently, you need to search with the exact spelling of the artist, album or track. Also, when visiting the website it is annoying to have to click on the sign in button every time.

The Verdict

I am going to keep my subscription active for the low fidelity service for the time being.