Microsoft Technology Licensing, LLC

Christopher Hakan Basoglu

Amit Kumar Agarwal

Hosam Adel Khalil

Sayan Dev Pathak

Shuangyu Chang

Emilian Y Stoimenov

Zoltan Romocsa

Ziad Al Bawab

Anand U Desai

Yifan Gong

Jian Wu

Kshitiz Kumar

Chaojun Liu

Nathan E Wohlgemuth

Naveen Parihar

Amy Parag Shah

Ajoy Nandi

Chun Hin Nelson Siu

Piyush Behre

Carmen Quan

Veljko Miljanic

Salman Quazi

Sharman W Tan

Aadyot Bhatnagar

Denis Fisenko

Min Hu

Md Nizam Uddin Chy

Ayush Vikram

Girish Milind Mahajan

Harini Kesavamoorthy

Osama Abuelsorour

Valeriy Viktorovich Kirshin

Sayan Pathak

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

A technique partitions a user's original query into plural smaller component queries, each of which has a common part and an instance-specific part. The technique distributes the component queries to plural processor instances of a processor. The plural processor instances transform the respective component queries into query-component responses by acting in parallel, independent of each other. The technique generates a final response based on the query-component responses, e.g., by assembling the component-query responses into the final response. The technique reduces latency because the processor instances work on parts of the user's original query at the same time, rather than as a single stream of consecutive tokens. The plural processor instances have access to a shared cache memory, and utilize relevant data that has been computed in response to previous queries.

Reducing latency by processing parts of a language model query in parallel

Techniques are provided for early processing of a part of a user input to produce a response to the entire or final user input. While the user input is being received, a partial user input, which is a part of the final user input, is processed to produce a response. The response is a candidate response for the final user input. After the final user input is received, and if the partial user input is determined to match or be equivalent to the final user input, the first response, which is already available, is provided to one or more output devices for presentation. If the final user input is determined to differ from the partial user input, the final user input is processed to produce a second response to the final user input, and the second response is provided for presentation. In some instances, multiple partial user inputs are received and processed.

Processing part of a user input to produce an early response

Disclosed speech recognition techniques improve user-perceived latency while maintaining accuracy by: receiving an audio stream, in parallel, by a primary (e.g., accurate) speech recognition engine (SRE) and a secondary (e.g., fast) SRE; generating, with the primary SRE, a primary result; generating, with the secondary SRE, a secondary result; appending the secondary result to a word list; and merging the primary result into the secondary result in the word list. Combining output from the primary and secondary SREs into a single decoder as described herein improves user-perceived latency while maintaining or improving accuracy, among other advantages.

User-perceived latency while maintaining accuracy

A data processing system implements obtaining a first textual content, segmenting the first textual content into a plurality of first segments, and providing each segment of the plurality of first segments to a first natural language processing (NLP) model to obtain a set of first readability scores for the plurality of first segments. The first NLP model is configured to analyze a textual input and to output a readability score representing a measurement of readability of the textual input. The system further implements aggregating the set of first segment readability scores to determine a first readability score for the first textual content, and perform at least one of causing the first readability score to be presented to a user or performing one or more actions on the first textual content based on the readability score.

Automated artificial intelligence driven readability scoring techniques

Acoustic features are batched into two different batches. The second batch of the two batches is made in response to a detection of a word hypothesis output by a speech recognition network that received the first batch. The number of acoustic feature frames of the second batch is equal to a second batch size greater than the first batch size. The second batch is also to the speech recognition network for processing.

Adaptive batching to reduce recognition latency

A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

Meeting-adapted language model for speech recognition

A system includes acquisition of a domain grammar, determination of an interpolated grammar based on the domain grammar and a base grammar, determination of a delta domain grammar based on an augmented first grammar and the interpolated grammar, determination of an out-of-vocabulary class based on the domain grammar and the base grammar, insertion of the out-of-vocabulary class into a composed transducer composed of the augmented first grammar and one or more other transducers to generate an updated composed transducer, composition of the delta domain grammar and the updated composed transducer, and application of the composition of the delta domain grammar and the updated composed transducer to an output of an acoustic model.

Online language model interpolation for automatic speech recognition

Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Growing community of inventors

Everett, WA, United States of America

Christopher Hakan Basoglu