Microsoft Technology Licensing, LLC

Padma Varadharajan

Shuangyu Chang

Piyush Behre

Wei Liu

Sarangarajan Parthasarathy

Michael Levit

Khuram Shahid

Nicholas Kibre

Issac Alphonso

Karthik Raghunathan

Umut Ozertem

Edward C Lin

Che Zhao

Cenk Ergan

Sayan Dev Pathak

Heiko Rahmel

Raymond Duane Parsons

Ravikant Gupta

Sharman W Tan

Sathish Kumar Manivannan

Keren Shushan

Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.

Custom display post processing in speech recognition

Systems generate segments of spoken language utterances based on different sets of segmentation boundaries. The systems are also configured to generate one or more formatted segments by assigning a punctuation tags at segmentation boundaries and to generate one or more final sentences from the one or more segments.

Streaming punctuation for long-form dictation

Examples of the present disclosure describe generation of a multi-arc confusion network to improve, for example, an ability to return alternatives to output generated. A confusion network comprising token representations of lexicalized hypotheses and normalized hypotheses is generated. Each arc of the confusion network represents a token of a lexicalized hypothesis or a normalized hypothesis. The confusion network is transformed into a multi-arc confusion network, wherein the transforming comprising realigning at least one token of the confusion network to span multiple arcs of the confusion network. Other examples are also described.

Transcription correction using multi-token structures

A system for reporting and analyzing problems encountered by computer users. The system includes a recording tool executing on a user computer to capture a sequence of user interactions in the context of a graphical user interface. When a problem or other stop event is encountered, the tool generates a report indicating user interactions leading to the stop event, including information such as the specific sequence of controls for specific programs accessed by the user. The report can be analyzed to identify a sequence of user interactions characteristic of a problem type, which in turn may be used to find a solution for a particular user's problem. The system may also include a server that receives and analyzes reports from multiple computer users to identify patterns of user interactions that characterize problem types. This information may be used for associating specific problems with future reports or to improve products.

Problem reporting system based on user interface interactions

Growing community of inventors

Palo Alto, CA, United States of America

Padma Varadharajan