Abstract: A computer-implemented method for providing a candidate list of alternatives for a text selection containing text from multiple input sources, each of which can be stochastic (such as a speech recognition unit, handwriting recognition unit, or input method editor) or non-stochastic (such as a keyboard and mouse). A text component of the text selection may be the result of data processed through a series of stochastic input sources, such as speech input that is converted to text by a speech recognition unit before being used as input into an input method editor. To determine alternatives for the text selection, a stochastic input combiner parses the text selection into text components from different input sources. For each stochastic text component, the combiner retrieves a stochastic model containing alternatives for the text component.

Abstract: A computer-implemented method for providing a candidate list of alternatives for a text selection containing text from multiple input sources, each of which can be stochastic (such as a speech recognition unit, handwriting recognition unit, or input method editor) or non-stochastic (such as a keyboard and mouse). A text component of the text selection may be the result of data processed through a series of stochastic input sources, such as speech input that is converted to text by a speech recognition unit before being used as input into an input method editor. To determine alternatives for the text selection, a stochastic input combiner parses the text selection into text components from different input sources. For each stochastic text component, the combiner retrieves a stochastic model containing alternatives for the text component.

Abstract: A method of correcting speech recognition mode errors in a document is disclosed. A computer-readable medium having computer-executable instructions for correcting speech recognition mode errors in a document is also disclosed. Further, an apparatus for correcting speech recognition mode errors in a document is disclosed.

Abstract: A background audio recovery system displays an inactive status indicator for a speech recognition program module in an application program. To prevent losses of dictated speech when a speech recognition program module is inadvertently assigned to an inactive mode, the background audio recovery system determines whether an audio input device is receiving audio. If audio is being received by the audio input device, the background audio recovery system stores the audio data for later retrieval by the user. When a user issues a command to activate the speech recognition program module, the background audio recovery system initiates a background audio program module for manipulating the stored audio data that was recorded while the speech recognition program module was assigned to an inactive mode.