Apparatus and method for normalizing input data of acoustic model and speech recognition apparatus
First Claim
Patent Images
1. An apparatus for normalizing input data of an acoustic model, the apparatus comprising:
- a window extractor configured to extract windows of frame data to be input to the acoustic model from frame data of a speech to be recognized; and
a normalizer configured to normalize the frame data to be input to the acoustic model in units of the extracted windows,wherein the normalizer is configured to normalize frames belonging to a current window in consideration of frames belonging to preceding windows of the current window.
1 Assignment
0 Petitions
Accused Products
Abstract
An apparatus for normalizing input data of an acoustic model includes a window extractor configured to extract windows of frame data to be input to an acoustic model from frame data of a speech to be recognized, and a normalizer configured to normalize the frame data to be input to the acoustic model in units of the extracted windows.
-
Citations
23 Claims
-
1. An apparatus for normalizing input data of an acoustic model, the apparatus comprising:
-
a window extractor configured to extract windows of frame data to be input to the acoustic model from frame data of a speech to be recognized; and a normalizer configured to normalize the frame data to be input to the acoustic model in units of the extracted windows, wherein the normalizer is configured to normalize frames belonging to a current window in consideration of frames belonging to preceding windows of the current window. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method of normalizing input data of an acoustic model, the method comprising:
-
extracting windows of frame data to be input to the acoustic model from frame data of a speech to be recognized; and normalizing the frame data to be input to the acoustic model in units of the extracted windows, wherein the normalizing of the frame data comprises normalizing frames belonging to a current window in consideration of frames belonging to preceding windows of the current window. - View Dependent Claims (8, 9, 10, 11, 12, 13)
-
-
14. A speech recognition apparatus comprising:
-
a preprocessor configured to; extract windows of frame data to be input to an acoustic model from frame data of a speech to be recognized; and normalize the frame data to be input to the acoustic model in units of the extracted windows; an acoustic score calculator configured to calculate acoustic scores in units of the normalized windows using the acoustic model based on a deep neural network (DNN); and an interpreter configured to; interpret the acoustic scores calculated in units of the normalized windows; and output a recognition result of the speech to be recognized based on the interpreted scores, wherein the preprocessor is further configured to normalize frames belonging to a current window in consideration of frames belonging to preceding windows of the current window. - View Dependent Claims (15, 16, 17, 18)
-
-
19. An apparatus for normalizing input data of an acoustic model, the apparatus comprising:
-
a window extractor configured to extract windows of frame data to be input to the acoustic model from frame data of a speech to be recognized; and a normalizer configured to normalize the frame data to be input to the acoustic model based on results of a determination that an amount of frame data to enable speech recognition is determined sufficient. - View Dependent Claims (20, 21, 22, 23)
-
Specification