In the last years, deep bidirectional recurrent neural networks (DBRNN) and DBRNN with long short-term memory cells (DBLSTM) have outperformed the most accurate classifiers for confidence estimation in automatic speech recognition. At the same time, we have recently shown that speaker adaptation of confidence measures using DBLSTM yields significant improvements over non-adapted confidence measures. In accordance with these two recent contributions to the state of the art in confidence estimation, this paper presents a comprehensive study of speaker-adapted confidence measures using DBRNN and DBLSTM models. First, we present new empirical evidences of the superiority of recurrent neural networks (RNN)-based confidence classifiers evaluated over a large speech corpus consisting of the English LibriSpeech and the Spanish poliMedia tasks. Second, we show new results on speaker-adapted confidence measures considering a multitask framework in which RNN-based confidence classifiers trained with LibriSpeech are adapted to speakers of the TED-LIUM corpus. These experiments confirm that speaker-adapted confidence measures outperform their non-adapted counterparts. Last, we describe an unsupervised adaptation method of the acoustic DBLSTM model based on confidence measures that results in better automatic speech recognition performance.

The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. Nowadays, state-of-the-art ST systems are populated with deep neural networks that are conceived to work in an offline setup in which the audio input to be translated is fully available in advance. However, a streaming setup defines a completely different picture, in which an unbounded audio input gradually becomes available and at the same time the translation needs to be generated under real-time constraints. In this work, we present a state-of-the-art streaming ST system in which neural-based models integrated in the ASR and MT components are carefully adapted in terms of their training and decoding procedures in order to run under a streaming setup. In addition, a direct segmentation model that adapts the continuous ASR output to the capacity of simultaneous MT systems trained at the sentence level is introduced to guarantee low latency while preserving the translation quality of the complete ST system. The resulting ST system is thoroughly evaluated on the real-life streaming Europarl-ST benchmark to gauge the trade-off between quality and latency for each component individually as well as for the complete ST system.

Although Long-Short Term Memory (LSTM) networks and deep Transformers are now extensively used in offline ASR, it is unclear how best offline systems can be adapted to work with them under the streaming setup. After gaining considerable experience on this regard in recent years, in this paper we show how an optimized, low-latency streaming decoder can be built in which bidirectional LSTM acoustic models, together with general interpolated language models, can be nicely integrated with minimal perfomance degradation. In brief, our streaming decoder consists of a one-pass, real-time search engine relying on a limited-duration window sliding over time and a number of ad hoc acoustic and language model pruning techniques. Extensive empirical assessment is provided on truly streaming tasks derived from the well-known LibriSpeech and TED talks datasets, as well as from TV shows on a main Spanish broadcasting station.

Multidisciplinary and multi-professional collaboration is vital in providing better outcomes for patients The aim of the INTERACT-EUROPE Project (Wide Ranging Cooperation and Cutting Edge Innovation As A Response To Cancer Training Needs) was to develop an inter-specialty curriculum. A pilot project will enable a pioneer cohort to acquire a sample of the competencies needed. A scoping review, qualitative and quantitative surveys were undertaken. The quantitative survey results are reported here. Respondents, including members of education boards, curriculum committees, trainee committees of European specialist societies and the ECO Patient Advisory Committee, were asked to score 127 proposed competencies on a 7-point Likert scale as to their value in achieving the aims of the curriculum. Results were discussed and competencies developed at two stakeholder meetings. A consultative document, shared with stakeholders and available online, requested views regarding the other components of the curriculum. Eleven competencies were revised, three omitted and three added. The competencies were organised according to the CanMEDS framework with 13 Entrustable Professional Activities, 23 competencies and 127 enabling competencies covering all roles in the framework. Recommendations regarding the infrastructure, organisational aspects, eligibility of trainees and training centres, programme contents, assessment and evaluation were developed using the replies to the consultative document. An Inter-specialty Cancer Training Programme Curriculum and a pilot programme with virtual and face-to-face components have been developed with the aim of improving the care of people affected by cancer.