Abstract: A system for automatically trimming an audio files based upon textual content associated with the audio file is provided. The source of the textual content may be an electronic document or written language text. The textual content may include predefined hints, a text mark, or end-of-phrase punctuation mark. The system generates a trimming instruction based upon textual content corresponding to the audio file, and the audio file is trimmed based upon the trimming instruction.

Abstract: A method (10) and system of adjusting a speech output rate to match a speech input rate can include the steps of receiving (12) speech input, computing (14) a speech input rate, and dynamically adjusting (18 or 26) a speech output rate to match the speech input rate. If the type of speech output is TTS, then a rate of TTS can be adjusted (18). If the type of speech output is recorded and alternate text is available, then steps (22 and 24) of counting alternate text available from a recorded output and determining an audio file length is used to compute a default output rate to adjust a recorded output rate. If the type is recorded and alternate text is unavailable, then steps (21 and 24) of obtaining an output word count from a transcription of a recorded speech output and determining an audio file length is used.

Abstract: A system and method is provided for optimizing the usability of a hierarchical menu in voice portal directory. A voice aggregator is programmed to rearrange the menu into a new hierarchical structure having a single layer. Portions of the hierarchy are partially restored if too many nodes, or duplicate nodes, are present at any selection step. Frequency of selection data are measured and applied to the nodes and used to order the nodes in the new hierarchy. Frequency of selection data are also used to determined which nodes are replaced in a hierarchy when it is partially restored.

Abstract: A method for alleviating ambiguity issues of new user defined speech commands. An original command for a user-defined speech command can be received. It can then be determined if the original command is likely to be confused with a set of existing speech commands. When confusion is unlikely, the original command can be automatically stored. When confusion is likely, a substitute command that is unlikely to be confused with existing commands can be automatically determined. The substitute can be presented as an alternative to the original command and can be selectively stored as the user-defined speech command.

Abstract: A vehicle ignition interlock system includes a breath analyzer and a controller operably connected to the breath analyzer and to an ignition system of the vehicle. The breath analyzer detects the breath alcohol level of a vehicle operator and is configured to prevent vehicle ignition if a breath alcohol level is greater than or equal to a threshold value. The controller requires the vehicle operator to periodically take breath analyzer “retests” after vehicle ignition in order to allow vehicle operation to continue. The breath analyzer also includes a mouth contamination sensor that is configured to distinguish between contaminants in the mouth of a vehicle operator and alcohol contained within a deep lung breath sample of the vehicle operator. The controller may require a breath alcohol retest of the vehicle operator via the breath analyzer in response to detecting the presence of a contaminant within the mouth of the vehicle operator.

Abstract: A system for automatically trimming an audio files based upon textual content associated with the audio file is provided. The source of the textual content may be an electronic document or written language text. The textual content may include predefined hints, a text mark, or end-of-phrase punctuation mark. The system generates a trimming instruction based upon textual content corresponding to the audio file, and the audio file is trimmed based upon the trimming instruction.

Abstract: A method, system and apparatus for dynamically alerting calling parties of menu structure changes in a telephone prompting system. In a telephone prompting system, a menu structure change alert method can include determining whether a menu structure change has occurred for the telephone prompting system in response to the receipt of an incoming call from a calling party. Subsequently, the calling party can be selectively alerted of the menu structure change. In this regard, an alert message can be played to the calling party.

Abstract: Methods, apparatus, and computer program products are described for providing oral modification of an ASR lexicon of an ASR engine that include receiving, in the ASR engine from a user through a multimodal application, speech for recognition, where the ASR engine includes an ASR lexicon of words capable of recognition by the ASR engine, and the ASR lexicon does not contain at least one word of the speech for recognition; indicating by the ASR engine through the multimodal application to the user that the ASR lexicon does not contain the word; receiving by the ASR engine from the user through the multimodal application an oral instruction to add the word to the ASR lexicon, where the oral instruction is accompanied by an oral spelling of the word from the user; and executing the instruction by the ASR engine.

Abstract: A method for providing driving directions can include the step of within a mobile telephone device, associating one or more of audio files with enabling GPS coordinates. The audio files can include digitally encoded speech that specify driving instructions. Current GPS coordinates for the mobile telephone device can be ascertained. When the current GPS coordinates match enabling GPS coordinates, the audio file associated with the enabling GPS coordinates can be played.

Abstract: A vehicle ignition interlock system includes a breath analyzer, a transdermal alcohol sensor configured to be worn by the vehicle operator, and a controller operably connected to the breath analyzer, to the transdermal alcohol sensor, and to an ignition system of the vehicle. The transdermal alcohol sensor is configured to be worn by the vehicle operator, and is configured to detect alcohol through the skin of the vehicle operator. The controller is configured to override one or more periodic breath analyzer retests if alcohol is not detected through the skin of the operator by the transdermal alcohol sensor. The controller is configured to increase the frequency of periodic breath analyzer retests of the vehicle operator in response to the transdermal alcohol sensor detecting alcohol through the skin of the operator. A proximity sensor detects proximity of the transdermal alcohol sensor relative to a vehicle operator area.

Abstract: A list presentation method. The list presentation method can include the steps of: dynamically grouping selected items in a list based on sequentially positioned symbols in the items which are common to one another; labeling each group of selected items; audibly presenting each group label through a speech user interface; and, responsive to a selection of one of the presented group labels, presenting through the speech user interface items in a group corresponding to the selected group label.

Abstract: A vehicle ignition interlock system includes a breath analyzer and a controller operably connected to the breath analyzer and to an ignition system of the vehicle. The breath analyzer detects breath alcohol level of a vehicle operator and prevents vehicle ignition if a breath alcohol level is greater than or equal to a threshold value. The controller requires the vehicle operator to periodically take breath analyzer “retests” after vehicle ignition in order to allow vehicle operation to continue. The breath analyzer includes first and second alcohol sensors. The second alcohol sensor is a backup for the first alcohol sensor and becomes operational if the first alcohol sensor malfunctions. The first or second alcohol sensors may be a mouth contamination sensor that distinguishes between mouth contaminants and alcohol contained within a deep lung breath sample. The system also includes sensors configured to detect impact (abuse) and vehicle motion.

Abstract: A vehicle ignition interlock system includes a breath analyzer and a controller operably connected to the breath analyzer and to an ignition system of the vehicle. The breath analyzer detects the breath alcohol level of a vehicle operator and is configured to prevent vehicle ignition if a breath alcohol level is greater than or equal to a threshold value. The controller requires the vehicle operator to periodically take breath analyzer “retests” after vehicle ignition in order to allow vehicle operation to continue. The breath analyzer also detects the presence of alcohol within the vehicle, such as alcohol emanating from an open container of alcohol. The controller may override one or more periodic retests if alcohol is not detected within the vehicle over a predetermined period of time. In addition, the controller may increase the frequency of periodic retests of the vehicle operator in response to detecting alcohol within the vehicle.

Abstract: A novel apparatus and method for correcting speech recognized text in a predominantly speech-only environment for use with a device having only a limited or no display device available. The method is preferably implemented by a machine readable storage mechanism having stored thereon a computer program, the method comprising the following steps. First, audio speech input can be received and speech-to-text converted to speech recognized text. Second, a first speech correction command for performing a correction operation on speech recognized text stored in a text buffer can be detected in the speech recognized text. Third, if a speech correction command is not detected in the speech recognized text, the speech recognized text can be added to the text buffer. Fourth, if a speech command is detected in the speech recognized text, the detected correction speech command can be performed on speech recognized text stored in the text buffer.

Abstract: A method and system for use with a computer based system having a touchscreen for distinguishing between a finger and a stylus. The method involves a series of steps including detecting contact with the touchscreen. Also, the method can include generating contact information for the detected contact with the touchscreen. The method includes comparing contact information corresponding to the detected contact with contact criteria, and, based on the comparison of the contact information, determining whether the contact was initiated by a finger or a stylus.

Abstract: A system for presenting database query results through an AUI can include a database manager for managing a database query operation on at least one database. The database query operation can produce database query result items. The system further can include a dialog manager for managing the presentation of the database query result items through the AUI concurrently with the database query operation. Notably, the AUI can include a text-to-speech processor for converting the database query result items into audible speech; and, a speech recognition engine for converting speech input into text recognizable by the dialog manager. The AUI further can include a barge-in facility. In one aspect of the invention, the system also can include a queue for storing database query result items from the database query operation; and, a queue manager for managing the insertion and removal of database query items to and from the queue.

Abstract: A method of generating language model statistics for a new word added to a language model incorporating at least one class file containing contextually related words. The method can include the following steps: First, language model statistics can be computed based on references to at least one incorporated class file. Second, a new word can be substituted for each reference to a selected class file. Additionally, the language model statistics can be re-computed based on the new word having been substituted for the reference. Third, the re-computed language model statistics can be displayed in a user interface and modifications can be accepted to the re-computed language model statistics through the user interface. Fourth, the language model statistics can be further re-computed based on the modifications. In consequence, the language model statistics are re-computed for the new word without introducing contextual inaccuracies in the language model.

Abstract: In a speech recognition system, a method of nonvisual enrollment comprising playing an audio representation of an enrollment script. As the enrollment is playing, shadowed speech from a user can be received, wherein the shadowed speech can lag the enrollment script. The received shadowed speech can be recorded for enrolling the user into the speech recognition system.