Systems and methods of pre-processing of speech signals for improved speech recognition

    公开(公告)号:US11270721B2

    公开(公告)日:2022-03-08

    申请号:US16418828

    申请日:2019-05-21

    Abstract: Pre-processing systems, methods of pre-processing, and speech processing systems for improved Automated Speech Recognition are provided. Some pre-processing systems for improved speech recognition of a speech signal are provided, which systems comprise a pitch estimation circuit; and a pitch equalization processor. The pitch estimation circuit is configured to receive the speech signal to determine a pitch index of the speech signal, and the pitch equalization processor is configured to receive the speech signal and pitch information, to equalize a speech pitch of the speech signal using the pitch information, and to provide a pitch-equalized speech signal.

    Communication device and communication system

    公开(公告)号:US10714119B2

    公开(公告)日:2020-07-14

    申请号:US16386089

    申请日:2019-04-16

    Inventor: Arun Rajasekaran

    Abstract: A communication device for a communication system is disclosed, which communication device comprises at least an I/O interface for connection with one or more audio sources to at least receive an input audio signal, a user audio output, an audio processor to provide an output audio signal to the user audio output from the input audio signal, and a reporting module. To improve the acoustic safety for a user of the communication device, the reporting module is configured to analyze the input audio signal and to determine, whether an acoustic safety incident is given, upon which the reporting module is configured to generate metadata of the acoustic safety incident.

    Systems and Methods of Pre-Processing of Speech Signals for Improved Speech Recognition

    公开(公告)号:US20190355385A1

    公开(公告)日:2019-11-21

    申请号:US16418828

    申请日:2019-05-21

    Abstract: Pre-processing systems, methods of pre-processing, and speech processing systems for improved Automated Speech Recognition are provided. Some pre-processing systems for improved speech recognition of a speech signal are provided, which systems comprise a pitch estimation circuit; and a pitch equalization processor. The pitch estimation circuit is configured to receive the speech signal to determine a pitch index of the speech signal, and the pitch equalization processor is configured to receive the speech signal and pitch information, to equalize a speech pitch of the speech signal using the pitch information, and to provide a pitch-equalized speech signal.

    Forking transmit and receive call audio channels

    公开(公告)号:US11588935B2

    公开(公告)日:2023-02-21

    申请号:US17185703

    申请日:2021-02-25

    Abstract: A method is disclosed for forking call audio channels. The method includes, during an active call, receiving a first audio stream of first call audio that originates from a far-end telephony device, and receiving a second audio stream of second call audio that originates from a microphone of a near-end headset. Further, the method includes generating, during the active call, a third audio stream containing the first call audio by processing the first audio stream, and generating a fourth audio stream containing the second call audio by processing the second audio stream. Still yet, the method includes, during the active call, generating a fifth audio stream containing the first call audio, and generating a sixth audio stream containing the second call audio.

    Control pod for a wireless headset
    15.
    发明授权

    公开(公告)号:US11281424B2

    公开(公告)日:2022-03-22

    申请号:US16987222

    申请日:2020-08-06

    Inventor: Arun Rajasekaran

    Abstract: A headset control pod stores a headset for charging when not in use. When the headset is in signal communication with a smart device, a user can use the control pod to mute and unmute a call of the smart device with no need to access the smart device. When the headset is used for music playback from the smart device, the control pod can be used to pause or advance playback. The control pod can also control playback by a headset of music stored in the control pod.

    Forking Transmit and Receive Call Audio Channels

    公开(公告)号:US20190098130A1

    公开(公告)日:2019-03-28

    申请号:US15719429

    申请日:2017-09-28

    CPC classification number: H04M3/42221 H04M3/568 H04M7/006

    Abstract: A method is disclosed for forking call audio channels. The method includes, during an active call, receiving a first audio stream of first call audio that originates from a far-end telephony device, and receiving a second audio stream of second call audio that originates from a microphone of a near-end headset. Further, the method includes generating, during the active call, a third audio stream containing the first call audio by processing the first audio stream, and generating a fourth audio stream containing the second call audio by processing the second audio stream. Still yet, the method includes, during the active call, generating a fifth audio stream containing the first call audio, and generating a sixth audio stream containing the second call audio. In addition, the method includes, during the active call, concurrently transmitting: the third audio stream, the fourth audio stream, the fifth audio stream, and the sixth audio stream.

    HEADSET SYSTEM WITH ACOUSTIC SAFETY INCIDENT DETECTION

    公开(公告)号:US20180262829A1

    公开(公告)日:2018-09-13

    申请号:US15457236

    申请日:2017-03-13

    Inventor: Arun Rajasekaran

    Abstract: A headset system with at least one or more headsets to provide output audio and a monitoring device is provided. The monitoring device is connected with the one or more headsets, which each comprise an audio processor to provide the output audio to a respective user from an input audio signal and a reporting module, configured to generate metadata of the output audio. The monitoring device is configured to receive the metadata from the one or more headsets and to determine, whether an acoustic safety incident is given. To reduce acoustic shocks to the user, the audio processor comprises a mode-switchable acoustic safety module with at least an enabled state and a disabled state, which acoustic safety module in the enabled state being configured to process the input audio signal to reduce acoustic shocks.

Patent Agency Ranking