Tag: privacy

Are you ready for a home that knows what you want before you do?

Imagine walking into a room in your smart home. The temperature is perfect, the lights turn on before you get there, and your favourite music is playing in the background. You feel instantly comfortable. It seems like magic! How does your smart home system know what you want without any prompts from you?  Read on to find out.

Intelligent presence prediction is the umbrella term for the seemingly magic anticipatory abilities of modern smart home products. The devices are able to ‘know’ what the user wants before they even know it themselves with two different, but complementary methods.

Nowcasting: The “Here and Now”

Nowcasting is about understanding what’s happening right now. Your motion sensors detect you’re in the room. Your door sensor shows you just arrived home. This is real-time intelligence—instant and reactive. It’s perfect for immediate actions like turning on lights when you enter a space or adjusting temperature the moment you wake up.

Think of it as your home paying attention in the present moment.

Forecasting: The Smart Prediction

Forecasting goes further. It learns your patterns and predicts what you’ll want before you need it. Based on your daily habits, calendar, location history, and preferences, your home anticipates your next move. Your thermostat warms up 15 minutes before you typically arrive home. Your bedroom lights dim automatically on Friday evenings because your home knows your weekend routine.

It’s not reacting—it’s thinking ahead.

Why Does This Matter?

While nowcasting keeps your home responsive and safe, forecasting transforms it from a reactive system into a truly anticipatory one. This means:

✦ Better comfort: No more entering a cold home or dark rooms
✦ True energy efficiency: Systems optimize before you arrive, not after
✦ Seamless experience: Your home feels like it understands your lifestyle
✦ Reduced friction: Fewer manual adjustments needed

The Future of Home Automation

The most advanced smart homes combine both approaches. They react instantly to what’s happening now while simultaneously predicting what comes next. It’s the difference between a home that responds to you and a home that anticipates you.

The line between convenience and intelligence is getting thinner. Are you ready for a home that doesn’t just react—but predicts?

Home Automation rules! Especially with  the new Aragon Maestro feature

Home Automation really does rule, now that the Home Automation Rules feature has been incorporated into the Aragon Maestro toolkit. This feature lets users create recurring automations using natural language input. Aragon Maestro can be controlled in real-time with on-the-spot voice commands. Now, with the new Home Automation Rules feature, actions can also be scheduled to work automatically during a period of the user’s choosing, or in relation to day/night natural light changes.

How It Works

The Home Automation Rules feature provides a web-based interface where users type commands in plain language to create automation rules. The system accepts input in English, French, or German. An on-device Large Language Model (LLM) processes these text commands and converts them into structured schedules that the Maestro then carries out automatically.

Examples of supported rules include:

  • “Turn on the kitchen lights 15 minutes before sunset every day.”
  • “Activate cozy scene at sunset on weekends.”
  • “Set the bedroom temperature to 22 degrees on weekday mornings.”
  • “Close all shutters at 10 PM on weekends.”

The web interface displays all active rules and allows users to add, edit, enable, disable, or delete them as needed.

Complete Privacy and Offline Operation

The Home Automation Rules feature operates entirely on-device with no cloud dependency. What’s said at home, stays at home!

On-device processing: Natural language parsing, rule scheduling, and command execution all happen locally on the Aragon Maestro. The system requires no internet connection for its core functions.

No data transmission: Automation rules are stored in a local database on the device. Nothing is transmitted to external servers or analyzed by third parties.

Reliable operation: Because the feature does not depend on internet connectivity, scheduled automations execute reliably regardless of network status.

What Can Be Automated

Any action that can be controlled through voice commands can also be scheduled as an automation rule. This includes:

  • Scenes: Activate predefined scenes such as “Movie Night” or “Good Morning” at specified times.
  • Lighting: Control lights to turn on at sunrise, dim to a specific percentage, or turn off at bedtime.
  • Shutters and blinds: Schedule blinds to open in the morning or close at sunset.
  • Heating: Set temperature targets for specific rooms at designated times.

Technical Implementation

The Home Automation Rules feature consists of three main components working together:

Natural Language Processing Engine: An on-board LLM interprets user input and extracts the command to execute along with scheduling details (time, days, solar events, and offsets). The system uses language-specific prompts to accurately parse commands in English, French, or German.

Scheduling System: A scheduling engine converts parsed rules into scheduled jobs. The system handles both fixed-time rules and solar-based triggers. For solar events like sunrise and sunset, the engine calculates precise times based on the user’s geographic location and updates these calculations daily to account for seasonal changes.

Execution Layer: When a scheduled time arrives, the system publishes the command to the same MQTT endpoint used by Aragon’s voice control system. This ensures that any command that works via voice will also function as a scheduled rule.

Multi-Language Support

The system provides native support for three languages. Users can write rules in their preferred language, and the LLM correctly interprets scheduling expressions such as:

  • English: “every weekday”, “at sunset”, “on weekends”
  • French: “les jours de semaine”, “au coucher du soleil”, “le week-end”
  • German: “an Wochentagen”, “bei Sonnenuntergang”, “am Wochenende”

The backend normalizes these expressions into a standardized format for consistent scheduling across languages.

User Interface

The web-based interface provides a straightforward workflow:

  1. Users enter a rule in natural language
  2. The system parses and validates the rule, showing the interpreted command and schedule
  3. Users confirm and create the rule
  4. All active rules are displayed in a list with options to edit, enable/disable, or delete

The interface also allows users to set their location (city or coordinates) to ensure accurate calculation of solar events.

Availability

The Home Automation Rules feature is available as a software update for all Aragon Maestro users. The update can be installed through the Maestro’s web interface. For more information about Aragon Maestro and its capabilities, visit heyaragon.com.

Spotify on Aragon – A Technical Overview

Spotify Voice Control use on Sonos via Aragon Maestro

Introducing Aragon Maestro’s new feature for controlling Spotify playback on Sonos speakers! This new solution is engineered with a privacy-first, offline-focused approach that leverages on-device processing for all sensitive actions. How does Aragon process the request? Read on to find out.

System Architecture and Data Flow

The control sequence from voice command to music playback is executed primarily on the local network, minimizing external communication.

  1. Voice Data Acquisition: A local network Aragon Satellite (WL or PoE) captures the user’s voice command requesting certain music. The raw audio data is streamed directly to the Aragon Maestro over the local network.
  2. On-Device Speech-to-Text (STT): Aragon Maestro processes the incoming audio stream using the on-board Whisper ASR model for speech-to-text conversion. This entire transcription process occurs locally on -device with no voice data sent to the cloud.
  3. On-Device Natural Language Processing (NLP): The resulting text string is fed into a local, on-device Large Language Model (LLM). This AI-driven model interprets the command, identifying the user’s intent, e.g., play, pause, skip, and the relevant information needed to carry out the command , e.g., artist name, song title, playlist. This allows the system to understand complex, natural language queries without relying on predefined vocabulary or cloud-based NLP services.
  4. Spotify API Interaction: Once the request is understood, the Aragon Maestro makes a targeted, anonymous query to the Spotify API. This is the only point of contact with an external cloud service. The purpose is strictly to enumerate tracks, albums, or artists based on the user’s request, and to retrieve the necessary identifiers for playback. No user-specific or personally identifiable information is transmitted by the Aragon system in this query.
  5. Local Sonos Control: Using track information from Spotify, the Maestro issues a command directly to the Sonos speaker(s) over the local area network (LAN). This instructs the Sonos system to stream the selected media directly from Spotify’s servers.

Key technical differences between Aragon and generic smart speakers

  • Private-by-Design: The entire voice processing pipeline (STT and NLP) is self-contained within the Aragon Maestro, ensuring user voice commands are never exposed to the internet.
  • Local Network Operation: All communication between Aragon Satellites, the Aragon Maestro, and the Sonos speakers occurs on the local network.
  • Minimal Cloud Footprint: The only external communication required is a stateless, anonymous request to the Spotify API for discovering music. There is no constant connection or data exchange with Aragon-hosted cloud services.
  • Integrated AI: The use of on-device Whisper and LLM technologies provide advanced, flexible voice control without need for an internet connection to process commands

Sound Event Detection – a new Aragon Maestro feature!

Aragon Maestro’s latest update introduces Sound Event Detection (SED). This is a sophisticated feature that enables real-time monitoring and classification of various acoustic events in the home environment. YAMNet neural network technology catagorises sounds into Alert, Human, Household, and Animal categories.

Sound Event Detection Overview

The Sound Event Detection (SED) feature in Aragon Maestro 2.1.0 processes audio streams from Aragon Satellites using UDP protocol, analyzing them for both wake words and sound events. This system employs YAMNet for sound classification, which therefore enables real-time detection and categorization of various acoustic events in the home environment. While the Maestro can handle multiple satellites simultaneously, it is recommended to configure only one satellite for SED during the initial deployment phase. To utilize SED, the satellite’s wake word system must be set to ‘Centralized’. This therefore allows the Maestro to manage wake word detection and enabling audio streaming for sound event analysis.

Configuring Sound Event Detection in Maestro

To set up SED in Aragon Maestro, follow these steps:

  • Update the system to Aragon Maestro version 2.1.0 and Wakeword (Central) to version 1.1.1 from the Maestro About page
  • Select the desired satellite and set its Wakeword system to ‘Centralized’
  • Save the configuration
  • Enable SED through the “Step 5. Configure ‘Sound Events’” dialog
  • Access the SED user interface at MAESTRO-IP:1880/dashboard/all

For optimal performance in this early release, we recommend that only one satellite should be configured for Sound Event Detection. The ‘Centralized’ Wakeword setting is crucial as it allows the Maestro to handle wake word detection and enables audio streaming for SED functionality.

Monitoring Interface Features

The SED monitoring interface is accessible at MAESTRO-IP:1880/dashboard/all. It offers a comprehensive view of detected sound events through five tabs: All Sounds, Alert, Human, Household, and Animal.

Each tab features:

  • A time chart with color-coded dots representing detected sounds by category
  • A Sound Event Gauge displaying instant detection values
  • A Sound Activity time chart for temporal visualization
  • A Sound Event list showing the latest events in text format

The ‘All Sounds’ tab provides an overview of all categories, while the other tabs offer detailed information specific to each sound type. This intuitive interface allows users to easily monitor and analyze various acoustic events in their environment, enhancing the overall functionality of the Aragon Maestro system.

Sound Categories and Notifications

The SED system categorizes sounds into four main groups: Alert, Human, Household, and Animal, each with specific detection thresholds and aliases. For instance, Alert sounds include alarms and glass breaking, while Human sounds encompass speech and physical noises. Users can configure custom notifications through Node-RED, integrating with pushover.net for remote alerts. In addition, for off-site monitoring, Tailscale VPN enables secure connections to the Maestro, allowing users to access the SED dashboard and examine detailed sound event charts from anywhere. This comprehensive approach ensures users stay informed about significant acoustic events in their environment, even when away from home.

Aragon Maestro Leads the AI-Driven Smart Assistant Market

We are pleased to announce the release of our new smart speaker, Aragon Maestro, a high-quality smart-home assistant with many new features that significantly enhance its overall capabilities. The Aragon Maestro puts offline home automation control on a whole new level with the on-device addition of AI-driven personal assistance features. This world-first represents an important advancement in voice control for home automation.

We have built on the success of our previous Aragon Master smart speaker to develop the next-generation Maestro. The product retains all its predecessor’s essential features, including on-board Node-RED and remote connection, coupled with a host of new AI-driven personal assistance features that function on-device.

aragon maestro
Aragon Maestro Functions Without the Cloud

The Aragon Maestro fills a gap in the smart-home market for a fail-safe smart speaker that functions in all situations, including in areas of poor connectivity. The Maestro’s independence from the Internet allows the users reliable and secure control of the smart environment. Consequently, this infallibility is of the utmost importance in use cases where the device is giving autonomy to disabled people, or to seniors living alone.

Exciting New Speech-To-Text Technology

The assistant understands complex queries without training on set vocabulary, thanks to reworked speech-to-text technology of the Aragon Maestro. This is due to the integration of an on-device LLM (Large Language Model). Therefore, the unit easily adapts to a wide variety of specific user requirements. This a necessary feature in smart solutions for senior- and disabled-care. The new technology opens up the sector to OEM for integrators or companies looking to offer bespoke smart solutions.

We have also made significant improvements in the Aragon Maestro’s capacity to understand wake-words and commands. The hybrid text-to-speech on-device system of Kaldi and Whisper technologies augment the capability of the smart speaker to understand commands. In addition, this holds true even in noisy environments.

As an additional feature, a to-do list can now be generated on-device. Although independent of cloud functionality, the list can be accessed remotely through an encrypted point-to-point remote connection.

High Interoperability

The Aragon Maestro is interoperable with a wide variety of standards. The product primarily controls KNX systems, however any IP is supported with some development. This facilitates the addition of the smart speaker into a large range of intelligent environments. The device is ready for installation in private homes, residential facilities, offices, and hotels.

The Aragon Maestro smart speaker is currently available for the English language. A progressive release is expected in Q3 of French and German models.

For more detailed information on the Aragon Maestro: https://heyaragon.com/product/aragon-maestro-en/

It is time to take your privacy seriously

Why we are no longer supporting Alexa

We have made a conscious choice not to ship hardware with direct support for the online voice assistants Alexa or Google Assistant.

Our Privacy Philosophy Benefits You.
We believe that:
  • Our customer should be able to be independent of us –  cloud-based service (e.g. Alexa Skill) is a service that must be made available on an Internet server day and night. This requires an infrastructure with financial and technical support.  We want to be honest with our clients, and cannot guarantee this service for the next 5, 10 or 20 years. Therefore, want to offer you a better solution for the future.
  • We should not have access to our customers’ installations – The skill not only allows the online voice assistant to access our customers’ installations, but also us at ProKNX, and anyone who should ever have access to our data pool. We do not want to bear this responsibility, as it is not in your best interests.
  • “What’s said at home, stays at home” – Our slogan is one that we truly believe in. Our development of ARAGON shows that today we are able to enable privacy and offer voice assistants offline. We refuse to support data and information theft.

Therefore, as of Sep 1, 2023, our “realKNX servers” will no longer support Alexa, Google Assistant, or remoteConnect.

What happens to the systems we have delivered so far?

For more information, go to our parent-site ProKNX

The Pyramid of Protected Privacy

Voice control with Privacy in focus

Aragon2 is our second-generation smart speaker. The original award-winning Aragon for Snips voice-controlled assistant was launched at the beginning of 2020 with the privacy of data as its primary focus.

The Aragon2 functions in an isolated network to control home automation devices, just like its predecessor, with all analysis of speech and execution of commands carried out on-device. This ensures the privacy of the user, and reliability of service.

Aragon2 differs from the original device by having augmented capabilities. When the smart speaker is in “online mode” the user has access to powerful online services like OpenAI/ChatGPT and Google.

Protected Mode – 100% Offline – Privacy guaranteed

In the Protected Mode, the Aragon system:

– Executes all home automation-related voice commands
– Speaks with a selectable voice, which also runs on the device.

But,

– Cannot update its software
– Cannot perform Network time synchronization over the Internet.

The solution: the Master is equipped with a battery to power the RTC. Additionally, all Satellites are equipped with special time synchronization software.

If you plan to run Aragon in an Internet disconnected network, add the Offline Kit to your basket.

Ideal for:

– Premises where the integrity of the users is an absolute requirement, e.g. executive meeting rooms
– Where Internet connection is limited, e.g. cruise ships and yachts.

Safe Mode – connected to the Internet

In Safe Mode, the Aragon system:

– Executes all home automation-related voice commands
– Speaks with a selectable voice, which also runs on the device.
– Uses Network time synchronization over the Internet
– Updates software at the user’s request. Additionally, Aragon
– Can optionally answer weather forecasts and traffic information queries.

No audio leaves the device, the voice commands are treated on the device (on-board ASR and NLU).

Ideal for:

– Premises where the integrity of the users is a requirement e.g. Homes, Offices, Hotels.

Trusted Services mode – Online-Offline

By adding the Trusted services, Aragon will be able to answer any query that you may ask OpenAI/ChatGPT and Google. Google search is accessed in a safe and anonymous manner via a proxy service, SerpAPI.

– ChatGPT by OpenAI is an artificial intelligence chatbot designed to engage in natural-sounding conversations. It utilizes the most advanced AI technology available today and can provide responses that are both coherent and accurate.

– SerpAPI is a powerful tool that enables access to Google and Bing search engine results pages, anonymously and with privacy.

How Trusted Service Mode Works

When the user switches to Trusted Service mode, Aragon uses an online service for transcription. This is necessary in order to understand users’ queries. The onboard Speech-to_text (or ASR) is trained and limited to Home Automation and media control tasks. To support the full English language, the audio is redirected to an external service.

The user enters online mode by saying Enter online mode and leave by saying Leave online mode. Aragon will automatically leave online mode after 1 hour of inactivity.

Before using online mode, the user must create free accounts for trusted online services.

Download your free copy of the privacy pyramid by clicking on the link below:

Aragon – Privacy by DesignDownload