10049668 is referenced by 2 patents and cites 4832 patents.

Systems and processes for converting speech-to-text are provided. In one example process, speech input can be received. A sequence of states and arcs of a weighted finite state transducer (WFST) can be traversed. A negating finite state transducer (FST) can be traversed. A virtual FST can be composed using a neural network language model and based on the sequence of states and arcs of the WFST. The one or more virtual states of the virtual FST can be traversed to determine a probability of a candidate word given one or more history candidate words. Text corresponding to the speech input can be determined based on the probability of the candidate word given the one or more history candidate words. An output can be provided based on the text corresponding to the speech input.

Title
Applying neural network language models to weighted finite state transducers for automatic speech recognition
Application Number
15/156161
Publication Number
10049668 (B2)
Application Date
May 16, 2016
Publication Date
August 14, 2018
Inventor
Ilya Oparin
Paris
FR
Rongqing Huang
Acton
MA, US
Agent
Dentons US
Assignee
Apple
CA, US
IPC
G10L 15/08
G10L 15/14
G10L 15/28
G10L 15/197
G10L 15/16
View Original Source