SPEECH RETRIEVAL METHOD AND APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM

WIPO Patent Application WO/2020/244150

A1

Provided are a speech retrieval method and apparatus, a computer device, and a storage medium. The method comprises: receiving a training set corpus and inputting same into an initial N-gram model for training to obtain an N-gram model (S110); receiving a speech to be recognized and recognizing said speech by means of the N-gram model to obtain the recognition result (S120); performing word segmentation on the recognition result to obtain a statement word segmentation result corresponding to the recognition result (S130); performing lexical analysis according to the statement word segmentation result to obtain a noun part-of-speech keyword corresponding to the statement word segmentation result (S140); and searching for corpora having the similarity with the noun part-of-speech keyword exceeding a preset similarity threshold in a pre-stored recommended corpus to obtain the retrieval result (S150).

JP4206253	Automatic voice response device and automatic voice response method
JP2000115335	COMMUNICATION EQUIPMENT AND REGISTRATION DATA MANAGEMENT METHOD AND STORAGE MEDIUM THEREOF
JP2006510933	Selection, adaptation, and combination of sensor-based speech recognition devices

HUANG JINLUN (CN)
CHEN LEI (CN)

PCT/CN2019/117872

December 10, 2020

November 13, 2019

Click for automatic bibliography generation  

PING AN TECH SHENZHEN CO LTD (CN)

G10L15/06; G06F16/63; G06F16/68; G10L15/22

CN110349568A	2019-10-18
CN109817217A	2019-05-28
CN107154260A	2017-09-12
CN105139239A	2015-12-09
CN106875941A	2017-06-20
CN109840323A	2019-06-04
CN107204184A	2017-09-26
CN107247759A	2017-10-13
CN109344830A	2019-02-15
JP2017003812A	2017-01-05

SHENZHEN TALENT PATENT SERVICE (CN)

View/Download PDF      PDF Help

Previous Patent: SEAT RESOURCE EXCHANGING METHOD, DEVICE, COMPUTER DEVICE, AND STORAGE MEDIUM

Next Patent: IMAGE PROCESSING METHOD AND APPARATUS, TERMINAL, AND STORAGE MEDIUM