Chapter 15 Acoustic information for timing

Author(s):  
Chris Button ◽  
Keith Davids
Keyword(s):  
2005 ◽  
Vol 168 (1-2) ◽  
pp. 1-10 ◽  
Author(s):  
Gabriella Musacchia ◽  
Mikko Sams ◽  
Trent Nicol ◽  
Nina Kraus

2021 ◽  
Vol 263 (6) ◽  
pp. 486-492
Author(s):  
Shuang Yang ◽  
Xiangyang Zeng

Underwater acoustic target recognition is an important part of underwater acoustic signal processing and an important technical support for underwater acoustic information acquisition and underwater acoustic information confrontation. Taking into account that the gated recurrent unit (GRU) has an internal feedback mechanism that can reflect the temporal correlation of underwater acoustic target features, a model with gated recurrent unit and Network in Network (NIN) is proposed to recognize underwater acoustic targets in this paper. The proposed model introduces NIN to compress the hidden states of GRU while retaining the original timing characteristics of underwater acoustic target features. The higher recognition rate and faster calculation speed of the proposed model are demonstrated with experiments for raw underwater acoustic signals comparing with the multi-layer stacked GRU model.


1996 ◽  
Vol 39 (3) ◽  
pp. 510-517 ◽  
Author(s):  
Jane C. Visto ◽  
Jerry L. Cranford ◽  
Rosalind Scudder

The present study investigated whether children with specific language impairment (SLI) differed from children with normal language learning in their ability to process binaural temporal information. The SLI group was matched with peers of the same chronological age, as well as peers with similar language age. All three subject groups were tested with measures of complex sound localization involving the precedence effect phenomenon. Subjects were required to track the apparent motion of a “moving” fused auditory image (FAI). Movement of the FAI was simulated by varying the delay incrementally between pairs of clicks presented, one each, from two matched loudspeakers placed on opposite sides of the child’s head. With this task, the SLI subjects’ performances were found to be similar to their language age-matched but chronologically younger peers. Both groups exhibited tracking skills that were statistically poorer than that of the chronologically age-matched group. Additional tests indicated this effect was not due to differences in motoric tracking abilities nor to the SLI subjects’ abilities to perceive small binaural time cues. Thus, children with SLI appear to be impaired in their ability to use binaural acoustic information in a dynamic ongoing fashion. The requirements for processing such nonlinguistic acoustic information in a “dynamic and ongoing” fashion may be similar to those involved in the ongoing processing of rapid changes in the temporal and spectral components of the speech chain.


Author(s):  
V. A. Shpak ◽  
◽  
E. S Kremlev ◽  
U. V. Mikhailova ◽  
◽  
...  

The article is devoted to the development of a virtual trainer for training information secu-rity specialists in the audit of premises in terms of acoustic safety requirements, including the search for secret intelligence device. The functional advantages of introducing virtual simula-tors into the educational process of higher education, such as accelerating and cheapening the learning process, are examined. The advantages and capabilities of the developed virtual train-er for assessing the security of acoustic information in a controlled room are describe


DYNA ◽  
2020 ◽  
Vol 87 (213) ◽  
pp. 9-16
Author(s):  
Franklin Alexander Sepulveda Sepulveda ◽  
Dagoberto Porras-Plata ◽  
Milton Sarria-Paja

Current state-of-the-art speaker verification (SV) systems are known to be strongly affected by unexpected variability presented during testing, such as environmental noise or changes in vocal effort. In this work, we analyze and evaluate articulatory information of the tongue's movement as a means to improve the performance of speaker verification systems. We use a Spanish database, where besides the speech signals, we also include articulatory information that was acquired with an ultrasound system. Two groups of features are proposed to represent the articulatory information, and the obtained performance is compared to an SV system trained only with acoustic information. Our results show that the proposed features contain highly discriminative information, and they are related to speaker identity; furthermore, these features can be used to complement and improve existing systems by combining such information with cepstral coefficients at the feature level.


Sign in / Sign up

Export Citation Format

Share Document