Microsoft Technology Licensing, LLC

Bruce Melvin Buntschuh

Michael Levit

Shuangyu Chang

Nick Kibre

On a computing device a speech utterance is received from a user. The speech utterance is a section of a speech dialog that includes a plurality of speech utterances. One or more features from the speech utterance are identified. Each identified feature from the speech utterance is a specific characteristic of the speech utterance. One or more features from the speech dialog are identified. Each identified feature from the speech dialog is associated with one or more events in the speech dialog. The one or more events occur prior to the speech utterance. One or more identified features from the speech utterance and one or more identified features from the speech dialog are used to calculate a confidence score for the speech utterance.

Leveraging interaction context to improve recognition confidence scores

Query history expansion may be provided. Upon receiving a spoken query from a user, an adapted language model may be applied to convert the spoken query to text. The adapted language model may comprise a plurality of queries interpolated from the user's previous queries and queries associated with other users. The spoken query may be executed and the results of the spoken query may be provided to the user.

User query history expansion for improving language model adaptation

A semantic error rate calculation may be provided. After receiving a spoken query from a user, the spoken query may be converted to text according to a first speech recognition hypothesis. A plurality of results associated with the converted query may be received and compared to a second plurality of results associated with the converted query.

Automatic semantic evaluation of speech recognition results

Architecture that employs an overall grammar as a set of context-specific grammars for recognition of an input, each responsible for a specific context, such as subtask category, geographic region, etc. The grammars together cover the entire domain. Moreover, multiple recognitions can be run in parallel against the same input, where each recognition uses one or more of the context-specific grammars. The multiple intermediate recognition results from the different recognizer-grammars are reconciled by running re-recognition using a dynamically composed grammar based on the multiple recognition results and potentially other domain knowledge, or selecting the winner using a statistical classifier operating on classification features extracted from the multiple recognition results and other domain knowledge.

Recognition using re-recognition and statistical classification

Sequential speech recognition using two unequal automatic speech recognition (ASR) systems may be provided. The system may provide two sets of vocabulary data. A determination may be made as to whether entries in one set of vocabulary data are likely to be confused with entries in the other set of vocabulary data. If confusion is likely, a decoy entry from one set of the vocabulary data may be placed in the other set of vocabulary data to ensure more efficient and accurate speech recognition processing may take place.

Growing community of inventors

Mountain View, CA, United States of America

Bruce Melvin Buntschuh