Search

Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine1,2. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes3. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation4,5. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning—a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine. © 2021, The Author(s).

This paper addresses errors in continuous Automatic Speech Recognition (ASR) in two stages: error detection and error type classification. Unlike the majority of research in this field, we propose to handle the recognition errors independently from the ASR decoder. We first establish an effective set of generic features derived exclusively from the recognizer output to compensate for the absence of ASR decoder information. Then, we apply a variant Recurrent Neural Network (V-RNN) based models for error detection and error type classification. Such model learn additional information to the recognized word classification using label dependency. As a result, experiments on Multi-Genre Broadcast Media corpus have shown that the proposed generic features setup leads to achieve competitive performances, compared to state of the art systems in both tasks. Furthermore, we have shown that V-RNN trained on the proposed feature set appear to be an effective classifier for the ASR error detection with an Accuracy of 85.43%.

Parkinson’s Disease (PD) affects motor capabilities of patients, who in some cases need to use human-computer assistive technologies to regain independence. The objective of this work is to study in detail the differences in error patterns from state-of-the-art Automatic Speech Recognition (ASR) systems on speech from people with and without PD. Two different speech recognizers (attention-based end-to-end and Deep Neural Network - Hidden Markov Models hybrid systems) were trained on a Spanish language corpus and subsequently tested on speech from 43 speakers with PD and 46 without PD. The differences related to error rates, substitutions, insertions and deletions of characters and phonetic units between the two groups were analyzed, showing that the word error rate is 27% higher in speakers with PD than in control speakers, with a moderated correlation between that rate and the developmental stage of the disease. The errors were related to all manner classes, and were more pronounced in the vowel /u/. This study is the first to evaluate ASR systems’ responses to speech from patients at different stages of PD in Spanish. The analyses showed general trends but individual speech deficits must be studied in the future when designing new ASR systems for this population.

There is ample evidence showing that listeners are able to quickly adapt their phoneme classes to ambiguous sounds using a process called lexically-guided perceptual learning. This paper presents the first attempt to examine the neural correlates underlying this process. Specifically, we compared the brain’s responses to ambiguous [f/s] sounds in Dutch non-native listeners of English (N=36) before and after exposure to the ambiguous sound to induce learning, using Event-Related Potentials (ERPs). We identified a group of participants who showed lexically-guided perceptual learning in their phonetic categorization behavior as observed by a significant difference in /s/ responses between pretest and posttest and a group who did not. Moreover, we observed differences in mean ERP amplitude to ambiguous phonemes at pretest and posttest, shown by a reliable reduction in amplitude of a positivity over medial central channels from 250 to 550 ms. However, we observed no significant correlation between the size of behavioral and neural pre/posttest effects. Possibly, the observed behavioral and ERP differences between pretest and posttest link to different aspects of the sound classification task. In follow-up research, these differences will be further investigated by assessing their relationship to neural responses to the ambiguous sounds in the exposure phase.

The Natural Speech Technology (NST) project is the UK's flagship research programme for speech recognition research in natural environments. NST is a collaboration between Edinburgh, Cambridge and Sheeld Universities; public sector institutions the BBC, NHS and GCHQ; and companies including Nuance, EADS, Cisco and Toshiba. In contrast to assumptions made by most current commercial speech recognisers, natural environments include situations such as multi-participant meetings, where participants may talk over one another, move around the meeting room, make non-speech vocalisations, and all in the presence of noises from oce equipment and external sources such as trac and people outside the room. To generate data for such cases, we have set up a meeting room/recording studio equipped to record 16 channels of audio from real-life meetings, as well as a large computing cluster for audio analysis. These systems run on free, Linux-based software and this paper gives details oftheir implementation as a case study for other users considering Linux audio for similar large projects.

The project Augmented Multi-party Interaction (AMI) is concerned with the development of meeting browsers and remote meeting assistants for instrumented meeting rooms - and the required component technologies R&D themes: group dynamics, audio, visual, and multimodal processing, content abstraction, and human-computer interaction. The audio-visual processing workpackage within AMI addresses the automatic recognition from audio, video, and combined audio-video streams, that have been recorded during meetings. In this article we describe the progress that has been made in the first two years of the project. We show how the large problem of audio-visual processing in meetings can be split into seven questions, like "Who is acting during the meeting?". We then show which algorithms and methods have been developed and evaluated for the automatic answering of these questions. © 2006 Springer-Verlag Berlin/Heidelberg.

The AMI Meeting Corpus is a multi-modal data set consisting of 100 hours of meeting recordings. It is being created in the context of a project that is developing meeting browsing technology and will eventually be released publicly. Some of the meetings it contains are naturally occurring, and some are elicited, particularly using a scenario in which the participants play different roles in a design team, taking a design project from kick-o' to completion over the course of a day. The corpus is being recorded using a wide range of devices including close-talking and far-field microphones, individual and room-view video cameras, projection, a whiteboard, and individual pens, all of which produce output signals that are synchronized with each other. It is also being hand-annotated for many different phenomena, including orthographic transcription, discourse properties such as named entities and dialogue acts, summaries, emotions, and some head and hand gestures. We describe the data set, including the rationale behind using elicited material, and explain how the material is being recorded, transcribed and annotated.