Esau Villatoro, research associate at the Speech & Audio Processing group at Idiap, and his colleagues from the Mathematics Research Center (CIMAT) from Mexico have won first place in two competitions related to Natural Language Processing. The objective of these competitions is to improve important aspects of Mexican society such as tourism and communication.
Idiap researchers published a paper describing an approach to speech processing based on the properties of the human brain. Their method proved as efficient as the current standard, whilst conserving the advantage of energy efficiency. Moreover, their work is replicable thanks to open access software paving the way for future applications.
Neural networks are often among cited technologies when it comes to artificial intelligence latest exploits. The downside is that this technology can be demanding in terms of energy costs. Two Idiap researchers demonstrated that in certain cases you should rather go for classical maths rather than for the AI hype.
In collaboration with a private company, Idiap researchers presented a novel approach to retrieve information from conversations’ transcripts. Their method uses both automatic speech recognition and natural language processing technologies.
In his research work, Idiap student, Bastian Schnell believes that affective TTS can be enabled with models which generalise better to the variability in speech thanks to components which are interpretable by humans.
Arriving in 2019 for a sabbatical year from the University of Mexico, Esaú Villatoro has now been working at Idiap for more than two years. Between publishing his work and adapting to Swiss life, he looks back on his experience at the institute.
Idiap Research Institute and the School of Engineering at EPFL invite applications for the directorship of Idiap. The successful candidate will also hold a faculty position as full professor at EPFL School of Engineering.
The Institute nominates every year two students for its internal awards. In 2021, the Best Paper Award goes to Suhan Shetty, and the Best Student Award goes to Parvaneh Janbakhshi. Congratulations!
Access to information is a challenge for disabled people, even at a time when communications channels are increasing. An international consortium gathering researchers, as well as private and public partners, under the leadership of the University of Zurich and including Idiap and Icare from the French speaking side of Switzerland was granted 6 million Swiss francs from Innosuisse—completed by 6 million from private partners—to take up this challenge.
“The deep artificial neural networks are inspired from the hierarchical structure of the human brain. Therefore, questioning the neural networks to learn robust, generalizable representations (abstractions) just like the human brain is not absurd, but challenging. However, revisiting fundamentals can be helpful.”
(August 30 - September 3, 2021, Brno, Czech Republic)
Understanding the impact of self-supervised pretraining approaches on low resource speech recognition.
Director of the Idiap Research Institute and Professor at EPFL, Hervé Bourlard is recognized for his major contributions to neural networks for statistical speech recognition. This distinction is awarded to him jointly with his colleague and long-time friend, Prof. Nelson Morgan of the International Computer Science Institute, and the University of California at Berkeley.
Obfuscating Voice Identity
Improving Swiss German speech recognition for Swisscom TV Box Voice Assistant
Idiap's speech group will be presenting six papers at ICASSP 2021. Our papers address a variety of research problems in pathological and physiological speech processing, automatic speech recognition, and machine learning.
“To understand others implies no only to get their point, but also to understand their feelings and emotions”; Daniel Goleman, Emotional Intelligence.
PARIDA Shantipriya, Idiap Postdoctoral Researcher has been granted to be an invited speaker at the Indo-German SPARC Symposium.
3rd ROXANNE Newsletter
Alternation in respiratory system and speech production system results in changes in speech. Therefore, speech signal, which can be acquired in a non-invasive manner, could be used to predict breathing patterns. There is a growing interest in that direction, which has gained further momentum with COVID-19 situation.
Highly Automated Air Traffic Controller Workstations with Artificial Intelligence Integration
A first step towards a Julia-based speech recognition toolkit.
You’re never far from an English word in Switzerland
As speech processing expands with diversified tasks, designing novel neural network models capable of learning meaningful speech representations gain importance.
This week Idiap's speech and machine learning group presented their joint work on Fast Transformers with Clustered Attention
Prof. Esaú Villatoto Tello, visitor professor at Idiap since September 2019, joins the SARAL project to work on the design of Cross-lingual Information Retrieval tools.
Lei joined Idiap in October 2019 for an internship in the framework of the China Scholarship Council visiting scholar program. During her internship, she worked on neural network-based mappings for single-channel dereverberation and noise reduction.
Roxanne is a EU-funded project that leverages text, speech and video in real-time in order to build tools for combating organized crime.
This week Idiap's speech group will be presenting five papers at Interspeech 2020, the largest conference for automatic speech processing. Our papers address a variety of research problems: Pathological speech processing, Multilingual automatic speech recognition, Automatic Speech Recognition for Air Traffic Control management and Speaker recognition.
Organized by the KIIT University, India, this 5 days program involved Idiap speakers.
Artificial intelligence to answer challenges of Mexican society
