Automatic language recognition on spontaneous speech has experienced a rapid development in the last few years. This development has been in part due to the competitive technological Language Recognition Evaluations (LRE) organized by the National Institute of Standards and Technology (NIST). Until now, the need to have clearly defined and consistent evaluations has kept some real-life application issues out of these evaluations. In particular, all past NIST LREs have used exclusively conversational telephone speech (CTS) for development and test. Fortunately this has changed in the current NIST LRE since it includes also broadcast speech. However, for testing only the telephone speech found in broadcast data will be used. In real-life applications, there could be several more types of speech and systems could be forced to use a mix of different types of data for training and development and recognition. In this article, we have defined a test-bed including several types of speech data and have analyzed how a typical language recognition system works using different types of speech, and also a combination of different types of speech, for training and testing.

In this paper we briefly describe the BioSec multimodal biometric database and analyze its use in automatic text-dependent speaker recognition research. The paper is structured into four parts: a short introduction to the problem of text-dependent speaker recognition; a brief review of other existing databases, including monomodal text-dependent speaker recognition databases and multimodal biometric recognition databases; a description of the BioSec database; and, finally, an experimental section in which speaker recognition results on some of these databases are presented and compared, using the same underlying speaker recognition technique in all cases.

This paper describes a new speech corpus, STC-TIMIT, and discusses the process of design, development and its distribution through LDC. The STC-TIMIT corpus is derived from the widely used TIMIT corpus by sending it through a real and single telephone channel. TIMIT is phonetically balanced, covers the dialectal diversity in continental USA and has been extensively used as a benchmark for speech recognition algorithms, especially in early stages of development. The experimental usability of TIMIT has been increased eventually with the creation of derived corpora, passing the original data through different channels. One such example is the well-known NTIMIT corpus, where the original files in TIMIT are re-recorded after being sent through different telephone calls, resulting in a corpus that characterizes telephone channels in a wide sense. In STC-TIMIT, we followed a similar procedure, but the whole corpus was transmitted in a single telephone call with the goal of obtaining data from a real and yet highly stable telephone channel across the whole corpus. Files in STC-TIMIT are aligned to those of TIMIT with a theoretical precision of 0.125 ms, making TIMIT labels valid for the new corpus. The experimental section presents several results on speech recognition accuracy.

The aim of this paper is to present the design of a multimodal database suitable for research on new possibilities for automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases can be very useful to give priority to their early treatment optimizing the expensive and time-consuming tests of current diagnosis methods based on full overnight sleep in a hospital. This work is part of an on-going collaborative project between medical and signal processing groups towards the design of a multimodal database as an innovative resource to promote new research efforts on automatic OSA diagnosis through speech and image processing technologies. In this contribution we present the multimodal design criteria derived from the analysis of specific voice properties related to OSA physiological effects as well as from the morphological facial characteristics in apnoea patients. Details on the database structure and data collection methodology are also given as it is intended to be an open resource to promote further research in this field. Finally, preliminary experimental results on automatic OSA voice assessment are presented for the collected speech data in our OSA multimodal database. Standard GMM speaker recognition techniques obtain an overall correct classification rate of 82%. This represents an initial promising result underlining the interest of this research framework and opening further perspectives for improvement using more specific speech and image recognition technologies.

In this paper we present our recent work to develop phonemic and syllabic inventories for Castilian Spanish based on the C-ORAL-ROM corpus, a spontaneous spoken resource with varying degrees of naturalness and in different communicative contexts. These inventories have been developed by means of a phonemic and syllabic automatic transcriptor whose output has been assessed by manually reviewing most of the transcriptions. The inventories include absolute frequencies of occurrence of the different phones and syllables. These frequencies have been contrasted against an inventory extracted from a comparable textual corpus, finding evidence that the available inventories, based mainly on text, do not provide an accurate description of spontaneously spoken Castilian Spanish.