Abstract: In fuel reservoir injection systems also known as common rail fuel-injection systems (1) for motor vehicles the problem exists that for a defined quantity of fuel that is about to be injected it is necessary to take into account not only the predominant pressure of the fuel but also its temperature. It is difficult to install and use a temperature sensor to detect the fuel temperature. The invention therefore proposes a method and a device for determining the temperature (T) from the pressure (P) measured by the pressure sensor (4) and the sound-propagation velocity (V) of a shock wave triggered at the moment of injection.

Abstract: A method for adjusting the duration of fuel injection through an injection valve is performed according to the temperature of the injected fuel. When in an operational mode, fuel is injected by the injection valve into a combustion chamber and non-injected fuel is discharged as a leakage flow. Fuel is supplied to the injection valve at a first high pressure. A first temperature of the fuel in the leakage flow and the pressure of the fuel in the fuel pressure store are measured. A second temperature of the fuel which is to be injected into the injection valve is determined according a function with the first temperature of the fuel in the leakage flow and the first pressure, and the duration of the fuel injection is adjusted according to the second temperature.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: Techniques are disclosed for automatically generating structured documents based on speech, including identification of relevant concepts and their interpretation. In one embodiment, a structured document generator uses an integrated process to generate a structured textual document (such as a structured textual medical report) based on a spoken audio stream. The spoken audio stream may be recognized using a language model which includes a plurality of sub-models arranged in a hierarchical structure. Each of the sub-models may correspond to a concept that is expected to appear in the spoken audio stream. Different portions of the spoken audio stream may be recognized using different sub-models. The resulting structured textual document may have a hierarchical structure that corresponds to the hierarchical structure of the language sub-models that were used to generate the structured textual document.

Abstract: A method of organizing an acoustic model for speech recognition is comprised of the steps of calculating a measure of acoustic dissimilarity of subphonetic units. A clustering technique is recursively applied to the subphonetic units based on the calculated measure of acoustic dissimilarity to automatically generate a hierarchically arranged model. Each application of the clustering technique produces another level of the hierarchy with the levels progressing from the least specific to the most specific. A technique for adapting the structure and size of a trained acoustic model to an unseen domain using only a small amount of adaptation data is also disclosed.

Abstract: A fuel injection apparatus for internal combustion engines, having a fuel injection pump inserted into the housing of the engine. A pump piston, which is driven axially back and forth in a cylinder bore, with one end face defines a pump work chamber from which a short injection line leads to an injection valve, and which can be made to communicate via a feed line with a fuel-filled low-pressure chamber. A magnetic valve disposed on the fuel injection pump controls the high-pressure feeding into the injection line. In order to avert an overly rapid return flow of fluid from the injection line into the pump work chamber, a return flow throttle valve is inserted into the injection line.