Microsoft Technology Licensing, LLC

Piyush Behre

Wei Liu

Shuangyu Chang

Nicholas Kibre

Sayan Dev Pathak

Edward C Lin

Che Zhao

Sharman W Tan

Jinyu Li

Amit Kumar Agarwal

Khuram Shahid

Christopher Hakan Basoglu

Yashesh Gaur

Heiko Rahmel

Issac Alphonso

Jian Xue

Padma Varadharajan

Zoltan Romocsa

Amy Parag Shah

Ayush Vikram

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

Some disclosed embodiments are directed to obtaining a decoded audio data including a spoken language utterance recognized in audio data and identifying a disfluency in the decoded audio data. Upon determining that correcting the disfluency would improve a readability score of the decoded audio data, the system generates a particular correction to correct the disfluency and applies the particular correction to the decoded audio data. Then, an updated decoded audio data is generated which reflects the particular correction. The updated decoded audio data has improved readability over the decoded audio data.

Systems and methods for GPT guided neural punctuation for conversational speech

Solutions for on-device streaming inverse text normalization (ITN) include: receiving a stream of tokens, each token representing an element of human speech; tagging, by a tagger that can work in a streaming manner (e.g., a neural network), the stream of tokens with one or more tags of a plurality of tags to produce a tagged stream of tokens, each tag of the plurality of tags representing a different normalization category of a plurality of normalization categories; based on at least a first tag representing a first normalization category, converting, by a first language converter of a plurality of category-specific natural language converters (e.g., weighted finite state transducers, WFSTs), at least one token of the tagged stream of tokens, from a first lexical language form, to a first natural language form; and based on at least the first natural language form, outputting a natural language representation of the stream of tokens.

On-device streaming inverse text normalization (ITN)

Growing community of inventors

Santa Clara, CA, United States of America

Piyush Behre