The use of syntax and multiple alternatives in the VODIS voice operated database inquiry system

The paper describes the architecture of VODIS, a voice operated database inquiry system, and presents some experiments which investigate the effects on performance of varying the level of a priori syntactic constraints. The VODIS system includes a novel mechanism for incorporating context-free grammatical constraints directly into the word recognition algorithm. This allows the degree of a priori constraint to be smoothly varied and provides for the controlled generation of multiple alternatives. The results show that when the spoken input deviates from the predefined task grammar, a combination of weak a priori syntax rules in conjunction with full a posteriori parsing on a lattice of alternative word matches provides the most robust recognition performance. © 1991.

The design and implementation of dialogue control in voice operated database inquiry systems

This paper describes work performed as part of the U.K. Alvey sponsored Voice Operated Database Inquiry System (VODIS) project in the area of intelligent dialogue control. The principal aims of the work were to develop a habitable interface for the untrained user; to investigate the degree to which dialogue control can be used to compensate for deficiencies in recognition performance; and to examine the requirements on dialogue control for generating natural speech output. A data-driven methodology is described based on the use of frames in which dialogue topics are organized hierarchically. The concept of a dynamically adjustable scope is introduced to permit adaptation to recognizer performance and the use of historical and hierarchical contexts are described to facilitate the construction of contextually relevant output messages. © 1989.

Mixed source model and its adapted vocal tract filter estimate for voice transformation and synthesis

In current methods for voice transformation and speech synthesis, the vocal tract filter is usually assumed to be excited by a flat amplitude spectrum. In this article, we present a method using a mixed source model defined as a mixture of the Liljencrants-Fant (LF) model and Gaussian noise. Using the LF model, the base approach used in this presented work is therefore close to a vocoder using exogenous input like ARX-based methods or the Glottal Spectral Separation (GSS) method. Such approaches are therefore dedicated to voice processing promising an improved naturalness compared to generic signal models. To estimate the Vocal Tract Filter (VTF), using spectral division like in GSS, we show that a glottal source model can be used with any envelope estimation method conversely to ARX approach where a least square AR solution is used. We therefore derive a VTF estimate which takes into account the amplitude spectra of both deterministic and random components of the glottal source. The proposed mixed source model is controlled by a small set of intuitive and independent parameters. The relevance of this voice production model is evaluated, through listening tests, in the context of resynthesis, HMM-based speech synthesis, breathiness modification and pitch transposition. © 2012 Elsevier B.V. All rights reserved.

Impact of Early Postnatal Androgen Exposure on Voice Development

Background: the impact of early postnatal androgen exposure on female laryngeal tissue may depend on certain characteristics of this exposure. We assessed the impact of the dose, duration, and timing of early androgen exposure on the vocal development of female subjects who had been treated for adrenocortical tumor (ACT) in childhood.Methods: the long-term effects of androgen exposure on the fundamental vocal frequency (F0), vocal pitch, and final height and the presence of virilizing signs were examined in 9 adult (age, 18.4 to 33.5 years) and 10 adolescent (13.6 to 17.8 years) female ACT patients. We also compared the current values with values obtained 0.9 years to 7.4 years after these subjects had undergone ACT surgery, a period during which they had shown normal androgen levels.Results: of the 19 subjects, 17 (89%) had been diagnosed with ACT before 4 years of age, 1 (5%) at 8.16 years, and 1 (5%) at 10.75 years. Androgen exposure (2 to 30 months) was sufficiently strong to cause pubic hair growth in all subjects and clitoromegaly in 74% (14/19) of the subjects, but did not reduce their height from the target value. Although androgen exposure induced a remarkable reduction in F0 (132 Hz) and moderate pitch virilization in 1 subject and partial F0 virilization, resulting in F0 of 165 and 169 Hz, in 2 subjects, the majority had normal F0 ranging from 189 to 245 Hz.Conclusions: Female laryngeal tissue is less sensitive to androgen exposure between birth and adrenarche than during other periods. Differential larynx sensitivity to androgen exposure in childhood and F0 irreversibility in adulthood are age-, concentration-, duration-, and timing-dependent events that may also be affected by exposure to inhibitory or stimulatory hormones. Further studies are required to better characterize each of these factors.