Joaquim Llisterri

The Corpus DIMEx100: transcription and evaluation

In this paper the transcription and evaluation of the corpus DIMEx100 for Mexican Spanish is presented. First we describe the corpus and explain the linguistic and computational motivation for its design and collection process; then, the phonetic antecedents and the alphabet adopted for the transcription task are presented; the corpus has been transcribed at three different granularity levels, which are also specified in detail. The corpus statistics for each transcription level are also presented. A set of phonetic rules describing phonetic context observed empirically in spontaneous conversation is also validated with the transcription. The corpus has been used for the construction of acoustic models and a phonetic dictionary for the construction of a speech recognition system. Initial performance results suggest that the data can be used to train good quality acoustic models.

A resource of errors written in Spanish by people with dyslexia and its linguistic, phonetic and visual analysis

In this work we introduce the analysis of DysList, a language resource for Spanish composed of a list of unique spelling errors extracted from a collection of texts written by people with dyslexia. Each of the errors was annotated with a set of characteristics as well as with visual and phonetic features. To the best of our knowledge, this is the largest resource of this kind in Spanish. We also analyzed all the features of Spanish errors and our main finding is that dyslexic errors are phonetically and visually motivated.

Identifying speaker‐dependent acoustic parameters in Spanish vowels

In the frame of VILE Projects (Inter‐and‐Intra‐Speaker‐Variation‐in‐Spanish for automatic speaker identification), we try to identify what vowels acoustic parameters depend more on the individual characteristics of the speaker and less of the linguistic variables. Variations on standard deviation (SD), when grouping together parameters by speaker or by phoneme, are analysed. 30 speakers (from AHUMADA database) read the same text in three sessions. Mean value (Hz) of four formants (F1‐F2‐F3‐F4) and fundamental frequency (F0) are analysed in Spanish vowels (except /u/), surrounded by unvoiced stops or /s/ (1850 samples). Hypothesis: Individual parameters will show less SD when grouping by speaker/session; vowel quality parameters, when grouping by phoneme. F1 and F2 are timbre‐dependent parameters. F3 and F4 are speaker‐dependent parameters. F0 has characteristics of both. The most variable parameter is F2. The opposite is F4. ‐No significant differences grouping by session or by speakers in none of the parameters. ‐F0 has the highest variability between vowel qualities, even if stressed and unstressed vowels are separated. ‐When clustering data by speaker/session (all vowels together), by comparison with clustering by vowel (all speakers together), SD is *50% higher in F1‐F2 *75% lesser in F4 *66% lesser in F0 *F3 shows no significant differences

TÉCNICAS Y PROCEDIMIENTOS PARA LA REPRESENTACIÓN DE LAS CURVAS MELÓDICAS

Este trabajo pretende presentar la complejidad que supone el analisis de los fenomenos asociados a la variacion melodica en el habla. Se propone que es necesario distinguir tres niveles de representacion: un nivel fonetico, uno fonologico y un nivel que represente la jerarquia de las unidades prosodicas. El nivel fonetico deberia incluir la curva melodica original, una representacion estilizada y una anotacion simbolica. El enfasis en los diferentes niveles dependera de los objetivos de la investigacion

Las tecnologías del habla en las lenguas románicas ibéricas

Abstract This paper reviews the development of speech technologies for Iberian Romance languages (Catalan, Galician, Spanish and Portuguese) with a special emphasis on the phonetic knowledge involved in the three core areas in the field: text-to-speech synthesis, automatic speech recognition and spoken language systems. Several important technological advances have taken place during the last decades and there is a substantial base of active researchers in the areas of engineering and computer science. However, the trend towards the use of automatic learning techniques and corpus-based models has seriously reduced the role of linguistics, favoring a reduction in time in the development of applications over basic research into the nature of the speech code.

Les tecnologies de la parla

Les tecnologies de la parla tenen com a objectiu facilitar la interaccio entre persones i ordinadors per mitja de la llengua oral, que es el nostre mitja de comunicacio mes natural. Per aquest motiu, son el resultat d’una recerca interdisciplinaria en la qual participen —o haurien de participar— els linguistes. En aquest article es preten mostrar com la conversio de text en parla, el reconeixement automatic de la parla i els sistemes de dialeg estan assolint un paper cada cop mes rellevant tant en la nostra vida quotidiana com en determinats entorns professionals; d’altra banda, s’exposa breument com poden contribuir tambe a millorar la integracio de determinats col·lectius.

La ingeniería lingüística en la sociedad de la información

Las necesidades que plantea la sociedad de la informacion determinan en cierta medida los objetivos de la linguistica computacional en el cambio de siglo: la revolucion tecnologica ha dado lugar a cambios en profundidad en los sectores productivos y las profesiones relacionadas con el lenguaje, y tambien en aquellos sectores que, sin estar directamente relacionados con el lenguaje, necesitan dotar su actividad del valor anadido de una comunicacion eficiente y fluida con clientes y usuarios. Esta nueva realidad impone la necesidad de desarrollar aplicaciones de procesamiento del lenguaje y del habla que tendran un amplio abanico de posibles usuarios y que han de tratar con centenares de millones de documentos escritos o sonoros, lo que a su vez implica la necesidad de disponer de recursos basicos de ingenieria linguistica que deben permitir el desarrollo efectivo de estas aplicaciones. En este articulo se presentan las principales tecnologias linguisticas, las relativas al tratamiento tanto del habla como del texto escrito, y su papel en el contexto europeo actual.