Audio Analytic feature on the popular AI Podcast with Noah Kravitz
From active noise cancellation to digital assistants that are always listening for your commands, audio is perhaps one of the most important but often overlooked aspects of modern technology in our daily lives.Audio Analytic has been using machine learning that enables a vast array of devices to make sense of the world of sound.Noah Kravits from the NVIDIA AI Podcast spoke with Dr Chris…
Audio Analytic's Alexandria dataset now contains over half-a-billion metadata points
At the heart of Audio Analytic's Alexandria™ data platform is the Alexandria dataset, the world’s largest, commercially-exploitable dataset for audio ML tasks. It now features 40 million labelled recordings across 1,200 sound classes and includes over half-a-billion metadata points.
Audio Analytic tops ABI Research’s deep learning sound processing competitive ranking
ABI Research – one of the world’s most respected analyst firms – conducted an independent and in-depth examination of deep learning (DL)-based ambient sound processing vendors and concluded that “Audio Analytic came out on top in the competitor ranking, scoring well across all criteria.”
Digital regulation inquiry brings House of Lords committee to Cambridge
Audio Analytic welcomed the House of Lords as part of an inquiry into the work of digital regulators by the Communications and Digital Select Committee.
Audio Analytic brings its industry perspective to the DCASE Workshop 2021
Today marks the start of DCASE Workshop 2021 with a full week of virtual keynotes, poster sessions, panels and town hall discussions.
Audio Analytic sets out long-term vision for the future of machine listening
Audio Analytic's vision is to create exceptional human experiences through a greater sense of hearing. The ability to teach machines to understand sound will play a foundational role in human-centered experiences which are pivotal to ambient intelligence/computing and the metaverse. A ‘greater sense of hearing’ will connect us to the past, help us be in the present and anticipate what we need in…
Audio Analytic granted patents in contextual awareness - the key to ambient computing
Audio Analytic is leading in the area of contextual awareness through machine listening. In fact, it was recently granted two patents in this area.
Why Audio Analytic's ‘soft temporal modelling’ design philosophy is key to understanding sounds
To guide Audio Analytic's research and development, the team set a core technical design philosophy that allows for the flexibility that is inherently needed to take very diverse sound objects and sequences and translate these into very stable and unique detections. As you learn and read more about Audio Analytic's technology, it is useful to understand how their approach runs through…
Audio Analytic is proud to sponsor DCASE 2021
Audio Analytic is excited to announce that for the fifth year running it is sponsoring the DCASE Workshop, alongside Bose, Apple, Google, Facebook, Dolby and others.
Consumer research shows strong demand for smart(er)phones that react to the world around them
Sound recognition will deliver a wave of new experiences on smartphones, and Audio Analytic's recent consumer research clearly shows a strong desire from users for these new AI-powered capabilities on their next device.
A compact sense of hearing enables innovative capabilities on new mass-market Qualcomm Snapdragon 778G
Audio Analytic has announced that its Media Tagging and Acoustic Scene Recognition technologies have been pre-validated and optimised for use with the new Qualcomm® Snapdragon™ 778G 5G Mobile Platform, , which has just been unveiled and will bring breathtaking 5G and AI performance and capabilities to the smartphone mass-market.
Audio Analytic contributes a lecture to Harvard’s TinyML online course
Audio Analytic is excited to have contributed a lecture to Harvard Professor Vijay Janapa Reddi’s course on Tiny Machine Learning (TinyML), alongside other industry experts from Google, Qualcomm, Microsoft and more.
'Be careful about how you get that data set' – AI industry warned by US Federal Trade Commission
Audio data quality is essential for sound recognition. There is, however, another reason why taking data seriously is so important: the significant financial and reputational risks that poor practice creates. This is the subject of a detailed whitepaper titled ‘Audio for Machine Learning: The Law and your Reputation‘ that Audio Analytic has published today.
Multiple sensory inputs: Sound plus movement patent delivers better user experiences
The combination of sound recognition and movement is the subject of a new patent, granted to Audio Analytic this week.
Audio Analytic named in CB Insights' AI 100 list of 'Most Innovative Artificial Intelligence Startups'
CB Insights has named Audio Analytic as one of the Top 100 Most Innovative Artificial Intelligence Companies in the world, as part of CB Insights AI 100 list.
Making ML work in the real world
In the latest series of TinyML UK talks, Dr Dominic Binks from Cambridge-based Audio Analytic recently presented on how to make ML work in the real world.
Qualcomm and Audio Analytic partnership: 2021 will be the year smartphones understand the acoustic world around us
Audio Analytic has announced that its ai3-nano™ software and Acoustic Scene Recognition AI technology is pre-validated and optimised to run in always-on, low-power mode running on the Qualcomm® Sensing Hub, part of the new Qualcomm® Snapdragon™ 888 5G Mobile Platform.
Why real sounds matter for machine learning
When it comes to training and evaluating sound recognition systems that perform to a high standard within a range of diverse consumer products, you cannot rely on recordings downloaded from the internet.
Loss function: There is more to DNNs than their architecture
In the world of machine learning, public attention is usually focused on the advent of new deep neural network (DNN) architectures, like when Geoffrey Hinton’s capsule networks promised to bring image recognition one step forward from convolutive networks. However, excitement for new DNN architectures is masking other factors of progress.
Audio Analytic wins ‘Best Overall AI Company’ in the AI Breakthrough Awards
Audio Analytic is proud to announce that it won ‘Best Overall AI Company’ in the 2020 AI Breakthrough Awards programme.
DCASE Challenge includes Audio Analytic's Polyphonic Sound Detection Score (PSDS) as one of the two evaluation metrics
The organisers of the 2020 DCASE Challenge have included Audio Analytic's Polyphonic Sound Detection Score (PSDS) as one of the two evaluation metrics for ‘Task 4: Sound event detection and separation in domestic environments’.
Audio Analytic at the tinyML Summit 2020: Engineering tinyML models in sound recognition
Earlier this year at the tinyML Summit in San Francisco, Dr Dominic Binks (VP Technology) from Audio Analytic took part in the poster session.
Audio Analytic's sound recognition technology will be at least 50% faster on Arm's new Cortex-M55 processor
Today, chip designer Arm has announced the new Arm Cortex-M55 processor which is promising to enhance on-device machine learning (ML) capabilities and signal processing for the smallest of IoT and embedded applications.
Polyphonic Sound Detection Score source code is now available on GitHub
First introduced in a research paper in late October 2019, Audio Analytic's Polyphonic Sound Detection Score (PSDS) is an industry-standard evaluation framework and metric for polyphonic sound recognition systems.
Sound recognition makes it into The Telegraph’s top picks of technology trends from CES 2020
Sound recognition has made it into The Telegraph’s top picks of the technology trends from CES 2020 that will be hitting the global markets this year.