NYX Ditech

Lets Talk!

Tag: virtual assistant

Categories
Technology

Top 5 Speakers Equipped With Alexa

Alexa Sonos One

Since Amazon has launched Alexa, it has been the talk of the town. It can smartly control all the smart home products, answer any questions you may have and play your favourite music as well. All of this can be done through the Amazon Echo speaker, however, Echo is not the best in the business when it comes to playing music.

Since Amazon opened its technology behind Alexa for everyone, several manufacturers have embraced Alexa and installed her in their own devices. The majority of them fall under the speaker category.

Here’s a list of top 5 speakers other than Amazon Echo which are equipped with Alexa and produce amazing sound.

1. KitSound Voice One

The KitSound Voice One is essentially an Amazon Echo, but with some serious audio grunt. It has been developed in collaboration with Amazon, to allow full Alexa experience. KitSound Voice One can answer questions, play music from various sources and control smart home devices. Also, It can hear you speak from the other side of the room and up to eight Voice One speakers can be connected together for multi-room playback.KitSound

2. Libratone Zipp

The Libratone Zipp is a portable speaker with interchangeable jackets and has an amazing sound output. Sound is produced 360-degrees and the overall profile can be adjusted using the companion app. The latest version has been updated to support Amazon Alexa as well, which means you can shoot commands at it, to change the music that’s playing, or turn your kitchen lights off. You can take Libratone Zipp on the go as well as it’s totally portable.

Libratone Zipp

3. Onkyo P3

The Onkyo P3 was first shown off at IFA 2017 and is now available to buy. With dual full-range drivers, dual passive bass radiators and DSP switching amplification, the Onkyo P3 has some serious sound power. With complete Alexa support, it is a great alternative to the Amazon Echo.

OnkyoP3

4. Polk Audio Command Bar

American audio manufacturer Polk Audio claim’s the title for world’s first soundbar with Alexa built in with the Command Bar. It essentially merges an Echo Dot with a full-fledged soundbar. That means the Command Bar can do anything which a Echo Dot can do, including controlling smart home products as well as source input, volume and bass levels.

Polk Audio Command Bar

Although it is set up for movies and TV shows first, it does great while playing music as well, which makes it a viable Echo alternative. It comes fitted with 1.25 x 3.25-inch full-range drivers, two 1-inch tweeters and ported wireless 6.5-inch subwoofer which are capable of producing loud and clear sound, thanks to the Polk’s Voice Adjust technology

5. Sonos One

If you want one of the best sounding speakers around, with multi-room capabilities and Alexa built-in, look no further. Sonos has made a powerful entry in the Alexa-enabled speaker market with the Sonos One. Later this year it will also offer Google Assistant, making it one of the most capable smart speakers around. It sounds fantastic and looks very attractive. It has the same design as the Play:1 except for on the top where there is a new control panel in place of the volume button on the Play:1

Sonos One

As soon as Amazon allowed the world to use the technology behind Alexa, a large number of companies included it into their products and posed a competition against Amazon’s own product equipped with Alexa. Only time will tell if it was a good move by the company. For more info on Alexa and the technology behind it, talk to our experts.

Categories
Technology

Alexa, What’s The Technology Behind You?

amazon-alexa

It was the early 90’s when speech recognition first took off with significant DARPA funding being invested in various research projects conducted by the top universities. However, the data available at that time was simply not sufficient for the technology to grow on. But that changed over the last decade due to substantial digital advancements that led to the availability of data at hand to train models. The biggest milestone achieved in the sphere of voice recognition technology is the Amazon Alexa that has used extremely complex machine learning processes to revolutionize the way we conduct everyday tasks.

Last year, Amazon opened up its technology behind Alexa, called the Lex. The system combines natural language understanding technology with automatic speech recognition and can be used by developers who want to build their own conversational applications like a chatbot. According to Amazon, the technology can be used to serve a variety of purposes especially web and mobile applications.

alexa-voice-text
image:techcrunch.com

So How Does This Technology Works?

1. Signalling Process

It all starts with the signal processing. This allows the device to make sense of the audio input by cleaning the signal. It’s one of the most crucial challenges in far-field audio. The primary objective is to recognise the target signal which can only be done by first identifying and minimizing ambient noises like the TV or the dishwasher. These issues are handled through beamforming which uses seven microphones to identify the source of the signal so that the device can focus on it. Moreover, acoustic echo cancellation knows when it’s playing and can eliminate that signal so only the important signal is left.

alexa-signalling-process

2. Wake Word Detection

Once the signalling is done the next task is Wake Word Detection. It determines if the user has said one of the words for which the device is programmed to turn on, such as ‘Alexa’. This is very important as voice commands could be picked from conversations around and may result in accidental purchases and angry customers. Furthermore, it needs to identify pronunciation differences as well and that too with limited CPU power and everything needs to be quick, so it requires high accuracy and low latency.

alexa-word-detection

3. Audio To Text Conversion

If the wake word is detected, the signal is then sent to the speech recognition software in the cloud. Here the audio is converted into text format. This process is performed by converting a binary classification problem into a sequence-to-sequence problem. It needs to browse through all the words in the English language to determine the input and produce the desired output. That’s huge, and the cloud is the only technology capable of scaling it sufficiently. The input is not a one-word query. It can be any possible question and therefore you need the context of it.

alexa-conversion

4. Natural Language Understanding (NLU)

Natural Language Understanding (NLU) is used to convert text into a meaningful representation. So, let’s say you ask for the weather in New York. Here, the intent would be weather and New York. But, the problem pops up with cross-domain intent classification. For example, if someone said ‘play remind me’, this is very different to remind me to go play. However, it could easily be misinterpreted. Additionally, there are a lot of commonly used words which sound the same but has completely different meanings. Like ‘BY’ can be misinterpreted as ‘BUY’ leading to unwanted consequences. Out-of-domain utterances are also eliminated at this stage if they don’t make any sense. This prevents the device from mistakenly hearing commands from televisions and the likes.

alexa-naturalimage:techcrunch.com

Researchers are working constantly to improve the speech recognition software. Further improvements will see Alexa better hold a conversation, remember what a person has said previously, and applying that knowledge to consequent interactions. Get into a discussion with our technology experts and analyse the future of Alexa.