End-to-end (E2E) Spoken Language Understanding (SLU) systems infer structured information directly from the speech signal using a single model. Due to the success of virtual assistants and the increasing demand for speech interfaces, these architectures are being actively researched for their potential to improve system performance by exploiting acoustic information and avoiding the cascading errors of traditional architectures. However, these systems require large amounts of specific, well-labelled speech data for training, which is expensive to obtain even in English, where the number of public audio datasets for SLU is limited. In this paper, we release the FalAI dataset, the largest public SLU dataset in terms of hours (250 hours), recordings (260,000) and participants (over 10,000), which is also the first SLU dataset in Galician and the first to be obtained in a low-resource scenario. Furthermore, we present new measures of complexity for the text corpora, the strategies followed for the design, collection and validation of the dataset, and we define splits for noisy audio, hesitant audio and audio where the sentence has changed but the structured information is preserved. These novel splits provide a unique resource for testing SLU systems in challenging, real-world scenarios.

This paper presents LSE_UVIGO, a multi-source database designed to foster research on Sign Language Recognition. It is being recorded and compiled for Spanish Sign Language (LSE acronym in Spanish) and contains also spoken Galician language, so it is very well fitted to research on these languages, but also quite useful for fundamental research in any other sign language. LSE_UVIGO is composed of two datasets: LSE_Lex40_UVIGO, a multi-sensor and multi-signer dataset acquired from scratch, designed as an incremental dataset, both in complexity of the visual content and in the variety of signers. It contains static and co-articulated sign recordings, fingerspelled and gloss-based isolated words, and sentences. Its acquisition is done in a controlled lab environment in order to obtain good quality videos with sharp video frames and RGB and depth information, making them suitable to try different approaches to automatic recognition. The second subset, LSE_TVGWeather_UVIGO is being populated from the regional television weather forecasts interpreted to LSE, as a faster way to acquire high quality, continuous LSE recordings with a domain-restricted vocabulary and with a correspondence to spoken sentences.

CORILSE is a computerized corpus of Spanish Sign Language (Lengua de Signos Española, LSE). It consists of a set of recordings from different discourse genres by Galician signers living in the city of Vigo. In this paper we describe its annotation system, developed on the basis of pre-existing ones (mostly the model of Auslan corpus). This includes primary annotation of id-glosses for manual signs, annotation of non-manual component, and secondary annotation of grammatical categories and relations, because this corpus is been built for grammatical analysis, in particular argument structures in LSE. Up until this moment the annotation has been basically made by hand, which is a slow and time-consuming task. The need to facilitate this process leads us to engage in the development of automatic or semi-automatic tools for manual and facial recognition. Finally, we also present the web repository that will make the corpus available to different types of users, and will allow its exploitation for research purposes and other applications (e.g. teaching of LSE or design of tasks for signed language assessment).

SEA_AP (Segmentador e Etiquetador Automático para Análise Prosódica, Automatic Segmentation and Labelling for Prosodic Analysis) toolkit is an application that performs audio segmentation and labelling to create a TextGrid file which will be used to launch a prosodic analysis using Praat. In this paper, we want to describe the improved functionality of the tool achieved by adding a dialectometric analysis module using R scripts. The dialectometric analysis includes computing correlations among F0 curves and it obtains prosodic distances among the different variables of interest (location, speaker, structure, etc.). The dialectometric analysis requires large databases in order to be adequately computed, and automatic segmentation and labelling can create them thanks to a procedure less costly than the manual alternative. Thus, the integration of these tools into the SEA_AP allows to propose a distribution of geoprosodic areas by means of a quantitative method, which completes the traditional dialectological point of view. The current version of the SEA_AP toolkit is capable of analysing Galician, Spanish and Brazilian Portuguese data, and hence the distances between several prosodic linguistic varieties can be measured at present.

The “Corpus Oral Informatizado da Lingua Galega (CORILGA)” project aims at building a corpus of oral language for Galician, primarily designed to study the linguistic variation and change. This project is currently under development and it is periodically enriched with new contributions. The long-term goal is that all the speech recordings will be enriched with phonetic, syllabic, morphosyntactic, lexical and sentence ELAN-complaint annotations. A way to speed up the process of annotation is to use automatic speech-recognition-based tools tailored to the application. Therefore, CORILGA repository has been enhanced with an automatic alignment tool, available to the administrator of the repository, that aligns speech with an orthographic transcription. In the event that no transcription, or just a partial one, were available, a speech recognizer for Galician is used to generate word and phonetic segmentations. These recognized outputs may contain errors that will have to be manually corrected by the administrator. For assisting this task, the tool also provides an ELAN tier with the confidence measure of each recognized word. In this paper, after the description of the main facts of the CORILGA corpus, the speech alignment and recognition tools are described. Both have been developed using the Kaldi toolkit.

The huge amount of multimedia information available nowadays makes its manual processing prohibitive, requiring tools for automatic labelling of these contents. This paper describes a framework for assessing a music detection tool; this framework consists of a database, composed of several hours of radio recordings that include different types of radio programmes, and a set of evaluation measures for evaluating the performance of a music detection tool in detail. A tool for automatically detecting music in audio streams, with application to music information retrieval tasks, is presented as well. The aim of this tool is to discard the audio excerpts that do not contain music in order to avoid their unnecessary processing. This tool applies fingerprinting to different acoustic features extracted from the audio signal in order to remove perceptual irrelevancies, and a support vector machine is trained for classifying these fingerprints in classes music and no-music. The validity of this tool is assessed in the proposed evaluation framework.

This article provides an overview of the dissemination work carried out in META-NET from 2010 until early 2014; we describe its impact on the regional, national and international level, mainly with regard to politics and the situation of funding for LT topics. This paper documents the initiative’s work throughout Europe in order to boost progress and innovation in our field.

This paper describes the CORILGA (“Corpus Oral Informatizado da Lingua Galega”). CORILGA is a large high-quality corpus of spoken Galician from the 1960s up to present-day, including both formal and informal spoken language from both standard and non-standard varieties, and across different generations and social levels. The corpus will be available to the research community upon completion. Galician is one of the EU languages that needs further research before highly effective language technology solutions can be implemented. A software repository for speech resources in Galician is also described. The repository includes a structured database, a graphical interface and processing tools. The use of a database enables to perform search in a simple and fast way based in a number of different criteria. The web-based user interface facilitates users the access to the different materials. Last but not least a set of transcription-based modules for automatic speech recognition has been developed, thus facilitating the orthographic labelling of the recordings.

This paper describes the result of a joint R&D project between Microsoft Portugal and the Signal Theory Group of the University of Vigo (Spain), where a set of language resources was developed with application to Text―to―Speech synthesis. First, a large Corpus of 10000 Galician sentences was designed and recorded by a professional female speaker. Second, a lexicon with phonetic and grammatical information of over 90000 entries was collected and reviewed manually by a linguist expert. And finally, these resources were used for a MOS (Mean Opinion Score) perceptual test to compare two state―of―the―art speech synthesizers of both groups, the one from Microsoft based on HMM, and the one from the University of Vigo based on unit selection.