Amazon Technologies, Inc.

Deepikaa Suresh

Stefano Stefani

Vikram Sathyanarayana Anbazhagan

Ashish Singh

Vasanth Philomin

Swaminathan Sivasubramanian

Vladimir Zhukov

Pramod Gurunath

Varun Sembium Varadarajan

Pu Paul Zhao

Faizaan Kersi Marolia

Vijit Gupta

Piyush Aggarwal

Ruoyu Huang

Rajkumar Gulabani

Praveen Kumar Akarapu

Sai Krishna Kuppaiah

Utsav Jain

Katrin Kirchoff

Techniques for streaming real-time automated speech recognition (ASR) are described. A user can stream audio data to a frontend service of the ASR service. The frontend service can establish a bi-directional connection to an audio decoder host to perform ASR on the data stream. The audio decoder host may include a streaming ASR engine which can analyze chunks of the audio data stream using an acoustic model to divide the audio data into words, and a language model to identify sentences made of the words spoken in the audio file. The acoustic model can be trained using short audio sentence data (e.g., on the order of 30 seconds to a few minutes), enabling the transcription service to accurately transcribe short chunks of audio data. The results are then punctuated and normalized. The resulting transcript is then streamed back to the user over the bi-directional connection.

Streaming real-time automatic speech recognition service

Techniques for automated speech recognition (ASR) are described. A user can upload an audio file to a storage location. The user then provides the ASR service with a reference to the audio file. An ASR engine analyzes the audio file, using an acoustic model to divide the audio data into words, and a language model to identify the words spoken in the audio file. The acoustic model can be trained using audio sentence data, enabling the transcription service to accurately transcribe lengthy audio data. The results are punctuated and normalized, and the resulting transcript is returned to the user.

Fully managed and continuously trained automatic speech recognition service

Embodiments presented herein provide techniques for evaluating for dynamically testing an application or 'app' on multiple computing devices at the same time. Each device participating in a testing session runs a device agent which monitors and records user input directed to the app on that device. When a user input event occurs is directed to the app on one of the devices, the corresponding device agent translates the user input into replication events that can be broadcast to, and then replayed by, the app on the other computing devices participating in the testing session.

Tool to replicate actions across devices in real time for improved efficiency during manual application testing

Growing community of inventors

Seattle, WA, United States of America

Deepikaa Suresh