An articulatorily constrained, maximum entropy approach to speech recognition and speech coding

Discriminative maximum entropy language model for speech recognition

10.21437/interspeech.2005-10 ◽

2005 ◽

Author(s):

Chuang-Hua Chueh ◽

To-Chang Chien ◽

Jen-Tzung Chien

Keyword(s):

Speech Recognition ◽

Maximum Entropy ◽

Language Model

Download Full-text

Comparison of Speech Recognition with Different Speech Coding Strategies (SPEAK, CIS, and ACE) and Their Relationship to Telemetric Measures of Compound Action Potentials in the Nucleus CI 24M Cochlear Implant System:Comparación del reconocimiento del lenguaje utilizando diferentes estrategias (SPEAK, CIS y ACE) y su relación con mediciones telemétricas de potenciales de acción compuestos, con el sistema de implante coclear nucleus CI24M

International Journal of Audiology ◽

10.3109/00206090109073098 ◽

2001 ◽

Vol 40 (1) ◽

pp. 32-42 ◽

Cited By ~ 66

Author(s):

Jan Kiefer ◽

Steffen Hohl ◽

Ekkehard Stürzebecher ◽

Thomas Pfennigdorff ◽

Wolfgang Gstöettner

Keyword(s):

Speech Recognition ◽

Cochlear Implant ◽

Action Potentials ◽

Speech Coding ◽

Coding Strategies ◽

Compound Action Potentials ◽

El Sistema ◽

Compound Action

Download Full-text

Effect of Frequency Boundary Assignment on Speech Recognition with the Nucleus 24 ACE Speech Coding Strategy

Journal of the American Academy of Audiology ◽

10.3766/jaaa.18.8.7 ◽

2007 ◽

Vol 18 (08) ◽

pp. 700-717 ◽

Cited By ~ 6

Author(s):

Marios S. Fourakis ◽

John W. Hawks ◽

Laura K. Holden ◽

Margaret W. Skinner ◽

Timothy A. Holden

Keyword(s):

Speech Recognition ◽

Speech Perception ◽

Cochlear Implants ◽

Speech Coding ◽

Frequency Assignment ◽

Speech Stimuli ◽

Unlimited Number ◽

Coding Strategy ◽

Technological Limitations ◽

Nucleus 24

The choice of frequency boundaries for the analysis channels of cochlear implants has been shown to impact the speech perception performance of adult recipients (Skinner et al, 1995; Fourakis et al, 2004). While technological limitations heretofore have limited the clinical feasibility of investigating novel frequency assignments, the SPEAR3 research processor affords the opportunity to investigate an unlimited number of possibilities. Here, four different assignments are evaluated using a variety of speech stimuli. All participants accommodated to assignment changes, and no one assignment was significantly preferred. The results suggest that better performance can be achieved using a strategy whereby (1) there are at least 7-8 electrodes allocated below 1000 Hz, (2) the majority of remaining electrodes are allocated between 1100 - 3000 Hz, and (3) the region above 3 kHz is represented by relatively few electrodes (i.e., 1-3). The results suggest that such frequency assignment flexibility should be made clinically available. La escogencia de límites de frecuencia para los canales de análisis de los implantes cocleares se ha visto que impacta el desempeño en la percepción del lenguaje de adultos implantados (Skinner y col, 1995; Fourakis y col, 2004). Mientras que las limitaciones tecnológicas hasta este momento han restringido la factibilidad clínica de investigar nuevas asignaciones de frecuencia, el procesador experimental SPEAR3 ofrece la oportunidad de investigar un número ilimitado de posibilidades. Aquí, se evalúan cuatro asignaciones diferentes utilizando una variedad de estímulos de lenguaje. Todos los participantes se acomodaron a los cambios de asignación y ninguna asignación tuvo una preferencia significativa. Los resultados sugieren que puede obtenerse un desempeño mejor utilizando una estrategia donde (1) existan al menos 7-8 electrodos colocados por debajo de 1000 Hz, (2) la mayoría de los electrodos remanentes sean colocados entre 1100 – 3000 Hz, y (3) la región por encima de 3 kHz esté representada por relativamente pocos electrodos (p.e., 1-3). Los resultados sugieren que tal flexibilidad en la asignación de frecuencias debería estar clínicamente disponible.

Download Full-text