Marta Casar

  • Citations Per Year
Learn More
This paper proposes a double layer speech recognition and utterance verification system based on the analysis of the temporal evolution of HMM’s state scores. For the lower layer, it uses standard HMM-based acoustic modeling, followed by a Viterbi grammarfree decoding step which provides us with the state scores of the acoustic models. In the second layer,(More)
Generally, speech recognition systems are based on one layer of acoustic HMM states where the recognition process consists on selecting a sequence of those states providing the best match with the speech utterance. In this paper we propose a new approach based on two layers. The first layer implements a standard acoustic modeling. The second layer models(More)
There is significant interest in developing new acoustic models for speech recognition that overcome traditional HMM restrictions. In this work, we propose to use a N-gram based augmented HMM. Two approaches are presented. The first one consists on overcoming the parameter independence assumption. This is achieved by modelling the dependence between the(More)
The development of new acoustical models that overcome traditional HMM restrictions is an active field of research in automatic speech recognition. One possible approach to achieve this goal is to work with N-gram based augmented HMM. In this paper, we propose to deal with time independence assumption of HMM using N-gram based modelling. For this, the(More)
The reliability and degradation mechanism of AlGaN/GaN single stage amplifiers after 10 GHz stress at a drain voltage of 42 V and channel temperatures above 250&#x00B0;C was investigated using electroluminescence (EL) imaging, infrared thermography, and TEM. The extrapolated median lifetime extracted from the Arrhenius plot is 510<sup>5</sup> h at a channel(More)
We report on technology, performance and reliability of state-of-the-art AlGaN/GaN MMICs for space applications. Our quarter-micron gate length HEMTs have breakdown voltages beyond 150 V and deliver 5 W/mm output power density at 30 V drain bias with 50% PAE at 10 GHz operating frequency. Packaged two-stage MMICs with 8 W output power for telemetry(More)
This paper proposes a double layer speech recognition and utterance verification system based on the analysis of the temporal evolution of HMM’s state scores. For the lower layer, it uses standard HMM-based acoustic modeling, followed by a Viterbi grammarfree decoding step which provides us with the state scores of the acoustic models. In the second layer,(More)
There is significant interest in developing new acoustic models for speech recognition that overcome traditional HMM restrictions. In this work, we propose to use Ngram based augmented HMMs. Two approaches are presented. The first one consists on overcoming the parameter independence assumption. This is achieved by modeling the dependence between the(More)