(57) ABSTRACT A processing unit can operate an end-to-end recurrent neural network (RNN) with limited contextual dialog memory that can be jointly trained by supervised …
BACKGROUND Computer-based speech recognition techniques have used local contexts (eg, previous 2 words uttered by a user) to predict a next word that a user is going to say. For …
D Yu - US Patent 10,249,305, 2019 - Google Patents
The techniques described herein improve methods to equip a computing device to conduct automatic speech recognition (“ASR”) in talker-independent multi-talker scenarios. In some …
IL Moreno, YJ Chen - US Patent 10,580,401, 2020 - Google Patents
SUMMARY A neural network, eg, a deep neural network, is trained, and used during runtime, with a reduced number of parameters provided to one or more layers in the neural …
Z Zhou, X Song - US Patent 11,615,785, 2023 - Google Patents
US11615785B2 - Speech recognition using natural language understanding related knowledge via deep feedforward neural networks - Google Patents US11615785B2 …
DZ Hakkani-Tur, X He, YN Chen - US Patent 10,262,654, 2019 - Google Patents
A computer-implemented technique is described herein for detecting actionable items in speech. In one manner of operation, the technique can include receiving utterance …
IA Kiss, HE Secker-Walker - US Patent 10,102,851, 2018 - Google Patents
Incremental speech recognition results are generated and used to determine a user's intent from an utterance. Utterance audio data may be partitioned into multiple portions, and …
BACKGROUND Computing devices can be used to process a user's spoken commands, requests, and other utterances into written tran Scriptions. Models representing data …
The present disclosure provides systems and methods that leverage machine-learned models (eg, neural networks) to provide enhanced communication assistance. In particular …