Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.

Abstract: A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method includes generating an unweighted grammar, selecting a database of words, generating a weighted grammar using the unweighted grammar and a statistical letter model trained on the database of words, receiving speech from a user after receiving the non-speech input and after generating the weighted grammar, and performing automatic speech recognition on the speech and non-speech input using the weighted grammar If a confidence is below a predetermined level, then the method includes receiving non-speech input from the user, disambiguating possible spellings by generating a letter lattice based on a user input modality, and constraining the letter lattice and generating a new letter string of possible word spellings until a letter string is correctly recognized.

Abstract: A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method includes generating an unweighted grammar, selecting a database of words, generating a weighted grammar using the unweighted grammar and a statistical letter model trained on the database of words, receiving speech from a user after receiving the non-speech input and after generating the weighted grammar, and performing automatic speech recognition on the speech and non-speech input using the weighted grammar. If a confidence is below a predetermined level, then the method includes receiving non-speech input from the user, disambiguating possible spellings by generating a letter lattice based on a user input modality, and constraining the letter lattice and generating a new letter string of possible word spellings until a letter string is correctly recognized.

Abstract: Systems and methods for unsupervised segmentation of multi-speaker speech or audio data by speaker. A front-end analysis is applied to input speech data to obtain feature vectors. The speech data is initially segmented and then clustered into groups of segments that correspond to different speakers. The clusters are iteratively modeled and resegmented to obtain stable speaker segmentations. The overlap between segmentation sets is checked to ensure successful speaker segmentation. Overlapping segments are combined and remodeled and resegmented. Optionally, the speech data is processed to produce a segmentation lattice to maximize the overall segmentation likelihood.

Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.

Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.

Abstract: A digital speech enabled middleware module is disclosed that facilitates interaction between a large number of client devices and network-based automatic speech recognition (ASR) resources. The module buffers feature vectors associated with speech received from the client devices when the number of client devices is greater than the available ASR resources. When an ASR decoder becomes available, the module transmits the feature vectors to the ASR decoder and a recognition result is returned.

Abstract: The invention provides a system and method for indexing and organizing voice mail message by the speaker of the message. One or more speaker models are created from voice mail messages received. As additional messages are left, each of the new messages are compared with existing speaker models to determine the identity of the callers of each of the new messages. The voice mail messages are organized within a user's mailbox by caller. Unknown callers may be identified and tagged by the user and then used to create new speaker models and/or update existing speaker models.

Abstract: A digital speech enabled middleware module is disclosed that facilitates interaction between a large number of client devices and network-based automatic speech recognition (ASR) resources. The module buffers feature vectors associated with speech received from the client devices when the number of client devices is greater than the available ASR resources. When an ASR decoder becomes available, the module transmits the feature vectors to the ASR decoder and a recognition result is returned.

Abstract: The invention provides a system and method for indexing and organizing voice mail message by the speaker of the message. One or more speaker models are created from voice mail messages received. As additional messages are left, each of the new messages are compared with existing speaker models to determine the identity of the callers of each of the new messages. The voice mail messages are organized within a user's mailbox by caller. Unknown callers may be identified and tagged by the user and then used to create new speaker models and/or update existing speaker models.

Abstract: A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method includes generating an unweighted grammar, selecting a database of words, generating a weighted grammar using the unweighted grammar and a statistical letter model trained on the database of words, receiving speech from a user after receiving the non-speech input and after generating the weighted grammar, and performing automatic speech recognition on the speech and non-speech input using the weighted grammar. If a confidence is below a predetermined level, then the method includes receiving non-speech input from the user, disambiguating possible spellings by generating a letter lattice based on a user input modality, and constraining the letter lattice and generating a new letter string of possible word spellings until a letter string is correctly recognized.

Abstract: A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method comprises performing spelling recognition via automatic speech recognition (ASR) on received speech from a user, the ASR being performed using a statistical letter model trained on domain data and producing a letter lattice RLN. If an ASR confidence is below a predetermined level, then the method comprises receiving non-speech input from the user, generating a keypad constraint grammar K and generating a letter string based on a composition of finite state transducers RLN and K. Other variations of the invention include recognizing input by first receiving non-speech input, dynamically generating an unweighted grammar, generating a weighted grammar using domain data, and then performing speech, and thus spelling, recognition on input speech using the weighted grammar.

Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.

Abstract: A digital speech enabled middleware module is disclosed that facilitates interaction between a large number of client devices and network-based automatic speech recognition (ASR) resources. The module buffers feature vectors associated with speech received from the client devices when the number of client devices is greater than the available ASR resources. When an ASR decoder becomes available, the module transmits the feature vectors to the ASR decoder and a recognition result is returned.

Abstract: Systems and methods for unsupervised segmentation of multi-speaker speech or audio data by speaker. A front-end analysis is applied to input speech data to obtain feature vectors. The speech data is initially segmented and then clustered into groups of segments that correspond to different speakers. The clusters are iteratively modeled and resegmented to obtain stable speaker segmentations. The overlap between segmentation sets is checked to ensure successful speaker segmentation. Overlapping segments are combined and remodeled and resegmented. Optionally, the speech data is processed to produce a segmentation lattice to maximize the overall segmentation likelihood.

Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

Abstract: A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method comprises performing spelling recognition via automatic speech recognition (ASR) on received speech from a user, the ASR being performed using a statistical letter model trained on domain data and producing a letter lattice RLN. If an ASR confidence is below a predetermined level, then the method comprises receiving non-speech input from the user, generating a keypad constraint grammar K and generating a letter string based on a composition of finite state transducers RLN and K. Other variations of the invention include recognizing input by first receiving non-speech input, dynamically generating an unweighted grammar, generating a weighted grammar using domain data, and then performing speech, and thus spelling, recognition on input speech using the weighted grammar.

Abstract: A digital speech enabled middleware module is disclosed that facilitates interaction between a large number of client devices and network-based automatic speech recognition (ASR) resources. The module buffers feature vectors associated with speech received from the client devices when the number of client devices is greater than the available ASR resources. When an ASR decoder becomes available, the module transmits the feature vectors to the ASR decoder and a recognition result is returned.