Cloze-style Zero-shot Named Entity Recognition “You Can Call Me Al” is the title of a 1980’s hit pop song by Paul Simon, and it’s not an unusual phrase to say. Unlike most things, people normally have names. That’s why, if someone wishes to write something down, you’re much more likely…
Protecting User Privacy with Voice Conversion With the increasing popularity of smart devices, more and more users have access to voice-based interfaces. Voice-based interfaces offer simple access to modern technologies and enable the development of new services. The building blocks behind these speech-based technologies are no longer handcrafted but learned…
Data annotation for Speech-to-Text and Natural Language Understanding What is Machine Learning? Machine learning refers to “Training AI algorithms to make decisions or predictions based on large amounts of data”. There are several types of machine learning techniques, depending on the amount of human knowledge provided as input: supervised learning,…
The COMPRISE Speech-to-Text-Translation: Discover the benefits! What is it? COMPRISE Speech-to-Text-Translation combines “Speech-to-Text” and “Machine Translation” in a smart way, to allow a user to speak his or her own language when interacting with a dialogue system that is internally designed for a different language. Why do I need it?…
Ethical concerns related to the use of voice technologies The ethical use of voice technologies, such as speech and voice recognition, is becoming more important every day. Devices such as smart speakers, smartphones or smartwatches collect massive amounts of data from users thanks to the wide range of activities they…
Recent times have seen a remarkable growth of interest for smart software that offers advanced features built upon cutting-edge artificial intelligence (AI) and machine learning (ML) methods, such as the ability to detect and adapt to voice commands, parse natural language, classify video and images, forecast more accurately complex financial…
The Accent Gap: What it is, and how to tackle it. Here is a quick introduction to the Accent Gap. What is the Accent Gap? The accent gap is the inability of voice technologies to understand speakers with non-native or regional accents with the same accuracy as the majority of…
Overview The COMPRISE Cloud Platform provides a highly scalable, open-source, cloud-based solution for the management of multilingual speech and text data and models. The COMPRISE Cloud Platform offers a web application programming interface (API) and a web-based user interface (UI) which allow users to upload, store and manage speech and…
Voice-based applications are still important. In fact, a survey by Adobe [Ref1] shows that during the COVID-19 pandemic the importance of voice-based applications has increased, thanks to their contactless interaction method and the desire for a safer, sanitary alternative. As much as one in three voice technology users mentioned hygiene…
The concept of data anonymisation Broadly speaking, data anonymisation can be defined as the process of irreversibly removing identifiable (confidential or private) information of both natural and legal persons[1] from raw datasets (e.g., text databases, audio recordings, etc.) [Ref1]. But there is more about anonymisation than what meets the eye,…
Discover COMPRISE Weakly Supervised NLU, an innovative automatic data labelling and model training software for Natural Language Understanding (NLU). Today’s Deep Learning technology is hungry for data – the more, the better. But for many tasks, raw data is not enough: every sample of data needs to be labelled first,…
The Cost Factor behind Speech-to-Text Technology Voice assistants equipped with Speech-to-Text technology have seen a major boost in performance and usage, thanks to the new powerful machine learning methods based on deep neural networks. These methods follow a supervised learning approach, requiring large amounts of paired speech-text data to train…
The emergence of e-commerce platforms combined with the mobile revolution has changed the way millions of users around the world discover, select and order goods. These platforms are evolving at an incredibly fast pace to become a complete environment in which end-users (i.e., customers) are able to place orders within…
In a world with more than 7,000 languages, roughly half of the people speak only one language, thus creating huge barriers that restrict cross-cultural communication. Thanks to advances in Artificial Intelligence and Machine Learning, we are steadily moving towards a future where hosting a dinner party for 20 guests, each…
Not just yet another note taking app Note taking apps are very useful in many situations. They can be used as a creative backlog for the user’s job, as a to-do list for household tasks or maybe as a shopping list. There are as many options as the number of…
Overview Are you a developer? Thanks to the COMPRISE SDK, you can now create multilingual, voice-enabled applications in a faster, cost-effective, and privacy-driven way. The SDK is made for Smartphone applications developed with the Ionic framework, with Angular as a foundation. It consists of: The COMPRISE Client Library, which can…
Voice-enabled technologies have become incredibly popular in the last few years. They are present in a wide variety of devices such as smartphones, house appliances, or smart speakers, and commonly in the form of voice assistants. Voice-enabled technologies can truly facilitate everyday tasks such as checking up the weather or…
Main Problems in Multi-Accent Speech-to-Text Systems English is one of the most widely spoken languages worldwide and there exists a large population of non-native speakers in English compared to other languages. However, accented speech samples may have heterogeneous characteristics due to the mother tongue or the proficiency of the speakers….
Introduction Voice-based applications are creating massive growth opportunities for European SMEs by enabling natural interaction with an ever-increasing range of services. Thanks to its naturalness and efficiency, voice has become a common means of accessing a range of services such as web search, car navigation, and smart home control. This…
How we did and what we learned from building a Covid-19 chatbot When hit by an unexpected crisis like the global spread of a new infectious disease, people are in dire need of trustworthy and reliable information, especially since there is no scenario or action plan ready to tackle the…
> The operating branch runs a spoken dialogue system on the user’s device or on a personal server. The dialogue outcomes are sent to the company delivering the desired service only. The training branch removes personal information from voice data using privacy driven text and voice transformers. The transformed data are sent to the COMPRISE Cloud-based Platform to train the spoken dialogue system. COMPRISE VOICE TRANSFORMER Prevents…
Since the invention of the very first smartphone, many things have changed. While the first apps were only provided by the developers themselves, there are nowadays app stores with millions of apps for nearly everything [Ref1]. Challenges when developing consumer applications While developing an app, the developer has to think…
In our previous posts [Post1] and [Post2], we have presented a rather streamlined version of the issue at hand and introduced quite a few simplifications along the way. Still, we have seen that privacy transformations of text are complex. A number of challenges presented themselves and we have discussed a…
Removing sensitive portions from a text, sometimes known as “sanitizing”, is often done by simply blackening the relevant words. Many people have seen such a redacted document at some point, it’s a technique commonly applied to classified government reports, for instance. A prominent example of such a document from recent…
“Tell me what you read and I tell you who you are.” – Pierre de La Gorce Voice assistants, such as Alexa, Siri, or Google Assistant, are becoming increasingly popular. Some users are, however, worried about the fact that their vocal interactions with these devices often get stored in the…
Today, voice-enabled technologies rely on a machine learning paradigm called deep learning. Deep learning has led to major improvements in speech-to-text, spoken language understanding, and dialogue management. Before moving into the GDPR principles, first, let’s first briefly recall the concepts of machine learning and deep learning introduced and detailed in…
Compatibility and integration are becoming essential features for voice technologies. The expected increase in the development of mid-level devices, which are able to connect with smart speakers, although not being fully smart themselves, serves as the perfect example [Ref1]. Despite the popularity of voice technologies, 41% of voice users report concerns on trust, privacy and…
Speech representation In order to process speech on computers, the microphone output is collected and represented as a waveform, which is nothing but a sequence of floating point values called amplitudes. Here is a snapshot of the Praat software which is commonly used for speech analysis. The top image shows…
To perform the tasks requested by users in the digital economy, voice-based technologies record and process large amounts of data, including personal data, which is centrally stored in the cloud. Voice-enabled systems capture the user’s speech signal (voice), but also background sounds! Background sounds can provide private information regarding the user…
Healthcare has been one of the countless beneficiaries of the revolutionary advances that widespread computing has brought. Fast, efficient data organisation, storage and access that have greatly sped up the medical enterprise, yet many low hanging fruits remain hanging. Chief among those is the increased application of technologies that can…
Voice-based technologies are capable not only of executing and interpreting commands but also of identifying individuals by using their voice only [Ref 1]. Voice recognition (a.k.a. speaker recognition) should not be confused with speech recognition. The former aims to verify the identity of the person speaking while the latter aims…
Talking about dialogue systems such as Alexa, Siri, or Google Assistant raises several questions. In the recent years, these virtual personal assistants have become the most popular representatives of their field. Although the quality of the communication and the supported languages are improving day by day, there are still several…
Ethics in retail Our partner Intermarché is one of the biggest food retailers in France, Belgium, Poland and Portugal. Intermarché is an ethics-centered retailer that aims to promote ethical values at all levels of the company from the production of goods to the customers’ basket through the whole supply chain…
On 25 May 2018, the General Data Protection Regulation (GDPR) came into force across the European Union. The new Regulation provides a broader definition of personal data with respect to its predecessor, the Data Protection Directive (DPD), and has rapidly become a standard for the processing of personal data not…
In July 2019, the Flemish news outlet VRT published an article revealing that internet giant Google employs thousands of people around the globe to listen to recordings of the customers – mostly unbeknownst to them. This came as quite a shock given that an almost identical report was previously published by the…
Voice assistants like Alexa, Siri, and Google Assistant are still a relatively new technology for the consumer market. However, under the label of “Spoken Dialog Systems” (SDS), it’s a research area that has quite a long history. The classical architecture of an SDS typically looks something like this: The user…
