Distinctive training methods and evaluation of a multilingual, multimodal speech training system
نویسنده
چکیده
A multilingual, multimodal speech teaching and training system has been developed for 5-10 years old speech handicapped children, in the frame of the SPECO Project, funded by the EU (Contract no. 977126) in 1999. During the training the patients see the speech pictures of the reference speech and listen to the sound of it at the same time. Thus they use the human visual and auditory feedback during their speech learning beside the tactile sensation. A detailed evaluation examination was prepared at the end of the development of the system. Firstly the opinion of speech therapists from different educational field that had been using the SPECO system in their work for a longer period was collected and summarized. Secondly, an objective evaluation was organized to examine the efficiency of the system. It became clear from the objective experiment and from the collection of the opinion of the speech therapists, that the system is a useful and effective teaching aid.
منابع مشابه
Generating Image Descriptions using Multilingual Data
In this paper we explore several neural network architectures for the WMT 2017 multimodal translation sub-task on multilingual image caption generation. The goal of the task is to generate image captions in German, using a training corpus of images with captions in both English and German. We explore several models which attempt to generate captions for both languages, ignoring the English outp...
متن کاملRapid Building of an ASR System for Under-Resourced Languages Based on Multilingual Unsupervised Training
This paper presents our work on rapid language adaptation of acoustic models based on multilingual cross-language bootstrapping and unsupervised training. We used Automatic Speech Recognition (ASR) systems in the six source languages English, French, German, Spanish, Bulgarian and Polish to build from scratch an ASR system for Vietnamese, an underresourced language. System building was performe...
متن کاملAn Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation
Different training and adaptation techniques for multilingual Automatic Speech Recognition (ASR) are explored in the context of hybrid systems, exploiting Deep Neural Networks (DNN) and Hidden Markov Models (HMM). In multilingual DNN training, the hidden layers (possibly extracting bottleneck features) are usually shared across languages, and the output layer can either model multiple sets of l...
متن کاملA scalable architecture for multilingual speech recognition on embedded devices
In-car infotainment and navigation devices are typical examples where speech based interfaces are successfully applied. While classical applications are monolingual, such as voice commands or monolingual destination input, the trend goes towards multilingual applications. Examples are music player control or multilingual destination input. As soon as more languages are considered the training a...
متن کاملLanguage Identification and Multilingual Speech Recognition Using Discriminatively Trained Acoustic Models
We perform language identification experiments for four prominent South-African languages using a multilingual speech recognition system. Specifically, we show how successfully Afrikaans, English, Xhosa and Zulu may be identified using a single set of HMMs and a single recognition pass. We further demonstrate the effect of language identification-specific discriminative acoustic model training ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002