公开(公告)号：US20190027130A1

公开(公告)日：2019-01-24

申请号：US16063052

申请日：2016-11-28

Applicant: SONY CORPORATION

Inventor： Emiru TSUNOO ,  Toshiyuki KUMAKURA

IPC: G10L15/01 ,  G10L15/22 ,  G10L15/32 ,  G06F17/27

Abstract: There is provided a speech processing apparatus to improve the flexibility of processing regarding speech recognition, the speech processing apparatus including: a determination unit configured to determine how to deal with a recognition result of speech data obtained by a first speech recognizer on a basis of a comparison between a certainty factor of the recognition result of the speech data obtained by the first speech recognizer and a threshold; and a threshold setting unit configured to set dynamically the threshold.

公开(公告)号：US20170229121A1

公开(公告)日：2017-08-10

申请号：US15515010

申请日：2015-11-17

Applicant: SONY CORPORATION

Inventor： Yuhei TAKI ,  Shinichi KAWANO ,  Takashi SHIBUYA ,  Emiru TSUNOO

IPC: G10L15/22 ,  G10L15/18 ,  G10L25/84 ,  G06F3/16 ,  G10L15/28

Abstract: There is provided an information processing device technology that enables an improvement in precision of sound recognition processing based on collected sound information, the information processing device including: a recognition controller that causes a speech recognition processing portion to execute sound recognition processing based on collected sound information obtained by a sound collecting portion; and an output controller that generates an output signal to output a recognition result obtained through the sound recognition processing. The output controller causes an output portion to output an evaluation result regarding a type of sound based on the collected sound information prior to the recognition result.