We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task. Previous works investigated the extreme case where source language transcription is not available during learning nor decoding, but we also study a midway case where source language transcription is available at training time only. In this case, a single model is trained to decode source speech into target text in a single pass. Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup. We also distribute the corpus and hope that our speech translation baseline on this corpus will be challenged in the future.
We describe a new challenge aimed at discovering subword and word units from raw speech. This challenge is the followup to the Zero Resource Speech Challenge 2015. It aims at constructing systems that generalize across languages and adapt to new speakers. The design features and evaluation metrics of the challenge are presented and the results of seventeen models are discussed.Index Terms-zero resource speech technology, subword modeling, acoustic unit discovery, unsupervised term discovery
Speech processing for under-resourced languages is an active field of research, which has experienced significant progress during the past decade. We propose, in this paper, a survey that focuses on automatic speech recognition (ASR) for these languages. The definition of under-resourced languages and the challenges associated to them are first defined. The main part of the paper is a literature review of the recent (last 8 years) contributions made in ASR for under-resourced languages. Examples of past projects and future trends when dealing with under-resourced languages are also presented. We believe that this paper will be a good starting point for anyone interested to initiate research in (or operational development of) ASR for one or several under-resourced languages. It should be clear, however, that many of the issues and approaches presented here, apply to speech technology in general (text-to-speech synthesis for instance).
International audienceThis paper summarizes the collaboration of the LIA and CLIPS laboratories on speaker diarization of broadcast news during the spring NIST Rich Transcription 2003 evaluation campaign (NIST-RTÕ03S). The speaker diarization task consists of segmenting a conversation into homogeneous segments which are then grouped into speaker classes. Two approaches are described and compared for speaker diarization. The first one relies on a classical two-step speaker diarization strategy based on a detection of speaker turns followed by a clustering process, while the second one uses an integrated strategy where both segment boundaries and speaker tying of the segments are extracted simultaneously and challenged during the whole process. These two methods are used to investigate various strategies for the fusion of diarization results. Furthermore, segmentation into acoustic macro-classes is proposed and evaluated as a priori step to speaker diarization. The objective is to take advantage of the a priori acoustic information in the diariza-tion process. Along with enriching the resulting segmentation with information about speaker gender
Abstract-Today, the growth of the aging population in Europe needs an increasing number of health care professionals and facilities for aged persons. Medical telemonitoring at home (and, more generally, telemedicine) improves the patient's comfort and reduces hospitalization costs. Using sound surveillance as an alternative solution to video telemonitoring, this paper deals with the detection and classification of alarming sounds in a noisy environment. The proposed sound analysis system can detect distress or everyday sounds everywhere in the monitored apartment, and is connected to classical medical telemonitoring sensors through a data fusion process. The sound analysis system is divided in two stages: sound detection and classification. The first analysis stage (sound detection) must extract significant sounds from a continuous signal flow. A new detection algorithm based on discrete wavelet transform is proposed in this paper, which leads to accurate results when applied to nonstationary signals (such as impulsive sounds). The algorithm presented in this paper was evaluated in a noisy environment and is favorably compared to the state of the art algorithms in the field. The second stage of the system is sound classification, which uses a statistical approach to identify unknown sounds. A statistical study was done to find out the most discriminant acoustical parameters in the input of the classification module. New wavelet based parameters, better adapted to noise, are proposed in this paper. The telemonitoring system validation is presented through various real and simulated test sets. The global sound based system leads to a 3% missed alarm rate and could be fused with other medical sensors to improve performance.
Statistical modeling of the speech signal has been widely used in speaker recognition. The performance obtained with this type of modeling is excellent in laboratories but decreases dramatically for telephone or noisy speech. Moreover, it is difficult to know which piece of information is taken into account by the system. In order to solve this problem and to improve the current systems, a better understanding of the nature of the information used by statistical methods is needed. This knowledge should allow to select only the relevant information or to add new sources of information.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.