Jorge Sommerhoff

Evaluación de la inteligibilidad del habla en español

Resumen es: En el ingles de Norteamerica existe un corpus de palabras foneticamente balanceadas (PB) para la medicion de la inteligibilidad del habla, estandarizado ...

Inteligibilidad acústica en español: una propuesta para su medición

Resumen es: El presente trabajo analiza el comportamiento de una lista de 1200 logatomos en espanol de estructura CVC (Consonante + Vocal + Consonante) con el objet...

Efectos acústicos de las variaciones fonopragmáticas y ambientales

En este trabajo se analiza el comportamiento del F0 y de los formantes en situaciones fonoprag-maticas y ambientales diversas. El corpus analizado esta integrado por 160 segmentos vocalicos correspondientes a una vocal “a” tonica inserta en ocho contextos foneticamente balanceados emitidos por una actriz en canal anecoico en situacion de lectura, evidencia, asombro, atenuacion y no-conclusion, y reproducidos luego todos ellos en canal telefonico, celular y reverberante. Los resultados muestran que las situaciones fonopragmaticas y ambientales causan variacio-nes en las propiedades acusticas de la senal. Los efectos producidos por estos factores no son homogeneos. El F0 y los formantes son afectados de diferente manera y grado.

Variabilidad idiofónica en español como herramienta forense

Resumen es: Este trabajo presenta aspectos metodologicos de una investigacion en curso y resultados parciales correspondientes a una parte del corpus experimental ob...

Estudio de la correlación entre STI y test de inteligibilidad subjetivo

Resumen es: La inteligibilidad de la palabra se puede medir por metodos subjetivos y objetivos. Sin embargo, los metodos objetivos deben tener la propiedad de poder ...

Comparison of the articulation test and speech transmission index values measured in two different acoustical poor conditions

In this work, a comparison is made between articulation tests and speech transmission index (STI) values, measured in the same place, in two different acoustically poor room conditions, both with STI values of less than 0.4. In the first room condition, a 200 m3 reverberation chamber with background noise of less than 32 dBA was used. In the second room condition, pink noise was added to a small room with reverberation time of less than 0.6 s, till values of STI lower than 0.4 were reached. The articulation test corpus consisted in a 1000 phonetically Spanish combination of a consonant, vowel, and consonant (CVC logatoms). The logatoms were recorded in an anechoic chamber. In the articulation test and STI measurement, both signals were emitted in the rooms using a NTI Talkbox with a sound power equivalent to a normal human voice. The STI and articulation was measured at the listeners seats which were located at different distances from the source but within STI values less than 0.4. The articulation test...

Corpus aspects to measure Spanish speech intelligibility: The methodology.

This study presents the methodology employed to develop a subjective measurement tool for Spanish speech intelligibility. It is an experimental corpus, consisting of logatoms with a consonant + vowel + consonant structure, including all phonetically possible combinations in Spanish, with data from the first stage of the ongoing research project Fondecyt Regular No. 1090249 (CONICYT) in order to draw up lists of logatoms to measure the articulation percentage and their correlation with the speech transmission index. The information provided will facilitate the local improvement of the acoustic quality when building public educational facilities and will also contribute to the national development of efficient habitability standards through a novel Spanish linguistic test aiming to serve as a reference for its application in the rest of the world’s Hispanic varieties.

Design and evaluation of reference populations with forensic purposes.

The present work analyzed the effect of sex, noise, vocal register, and channel on the performance of Batvox, the automatic speech recognizer employed by the Forensic Laboratory of the Investigative Police of Chile. This study transferred and applied the methodology and results of a previous and recently finished research project [Regular Fondecyt No. 1,070,210, funded by the National Commission for Scientific and Technological Research of the Government of Chile] to develop a model for the generation of speech reference populations with forensic purposes, which incorporated a set of dialect and environmental variables not considered in the selected samples currently integrating their databases. The information supplied provided methodological criteria to develop an optimized database for the biometric identification of speakers in Chile and to improve the performance of the systems applying them.

Implicancias y proyecciones forenses en el análisis de la voz

Resumen es: Este articulo describe los efectos de las condiciones fonopragmaticas y ambientales sobre el F0 y los formantes y senala la falta de datos empiricos y/o ...