Abstract: Method and apparatus for speech processing are disclosed. A first unvoicing parameter for a first frame of a speech signal is determined, and furthered smoothed based on a second unvoicing parameter for a second frame prior to the first frame. A difference between the first unvoicing parameter and the smoothed unvoicing parameter for the first subframe is computed and a unvoiced/voiced classification of the first frame is determined using the computed difference as a decision parameter. Further processing, such as Bandwidth extension (BWE) is performed on based on the classification of the first frame.

Abstract: A network device is connected to user device and includes a processor and a memory storing executable code executed by the processor. The network device is configured to receive first keyword data and speech data followed by the first keyword data; determine whether the first keyword data corresponds to a first keyword; in response to determining that the first keyword data corresponds to the first keyword, recognize word information from the speech data to generate at least one word recognition result; send the at least one word recognition result through a first communication path to a first network; and in response to determining that the first keyword data corresponds to a second keyword, stop recognizing the word information from the speech data followed by the first keyword data, and send the speech data through a second communication path to the first user device.

Abstract: An electronic device and a method for recognizing a speech are provided. The method for recognizing a speech by an electronic device includes: receiving sounds generated from a sound source through a plurality of microphones; calculating power values from a plurality of audio signals generated by performing signal processing on each sound input through the plurality of microphones and calculating direction information on the sound source based on the calculated power values and storing the calculated direction information; and performing the speech recognition on a speech section included in the audio signal based on the direction information on the sound source. As a result, the electronic device may correctly detect only a speech section from an audio signal while improving a speech section detection related processing speed.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a device comprising a processor detects a communication session between a calling device and a called device, and receives a motion signal from the called device; the motion signal is generated at a motion sensor of the called device during or after the communication session. The device analyzes the motion signal to determine whether a portion of the motion signal corresponds to a preselected motion of the called device and whether a subsequent call from the calling device accordingly is to be blocked. Responsive to a determination that the subsequent call is to be blocked, the device also updates a list of blocked caller identifiers associated with the called device to add an identifier associated with the calling device. Other embodiments are disclosed.

Abstract: A method for speech processing includes determining an unvoicing parameter for a first frame of a speech signal and determining a smoothed unvoicing parameter for the first frame by weighting the unvoicing parameter of the first frame and a smoothed unvoicing parameter of a second frame. The unvoicing parameter reflects a speech characteristic of the first frame. The smoothed unvoicing parameter of the second frame is weighted less heavily when the smoothed unvoicing parameter of the second frame is greater than the unvoicing parameter of the first frame. The method further includes computing a difference, by a processor, between the unvoicing parameter of the first frame and the smoothed unvoicing parameter of the first frame, and determining a classification of the first frame according to the computed difference. The classification includes unvoiced speech or voiced speech. The first frame is processed in accordance with the classification of the first frame.

Abstract: In accordance with an embodiment of the present invention, a method for speech processing includes determining an unvoicing/voicing parameter reflecting a characteristic of unvoiced/voicing speech in a current frame of a speech signal comprising a plurality of frames. A smoothed unvoicing/voicing parameter is determined to include information of the unvoicing/voicing parameter in a frame prior to the current frame of the speech signal. A difference between the unvoicing/voicing parameter and the smoothed unvoicing/voicing parameter is computed. The method further includes generating an unvoiced/voiced decision point for determining whether the current frame comprises unvoiced speech or voiced speech using the computed difference as a decision parameter.

Abstract: A conference mixer includes a unit configured to receive a plurality of input streams, a spectral voice activity detection (VAD) unit configured to, for each of the input streams, generate and output a spectral VAD decision indicating whether a frame including data packets is voice, a turbo VAD unit configured to generate and output a turbo VAD decision that indicates for a frame including data packets which input stream is active, the turbo VAD decision being based on the spectral VAD decisions and a power-based decision indicating whether an estimated instantaneous power level of a frame including data packets is greater than a power threshold, and a finite state machine (FSM) unit configured to select which of the input streams to output as an active stream based on a plurality of the turbo VAD decisions, the turbo VAD decision being based in part on feedback provided by the FSM.

Abstract: Methods, systems, and apparatus are provided for multiple-input multiple-output acoustic echo cancellation. A multiple-input multiple-output acoustic echo canceller (MIMO AEC) is provided as a high quality echo canceller for voice and/or audio communication over a network (e.g., packet switched network). The MIMO AEC is an extension of, as well as an application/usage of a single-input single-output acoustic echo canceller (“mono AEC”). The MIMO AEC is an extension of the mono AEC in that the code/theory underlying the mono AEC is adjusted for use with multiple channels. The manner in which AEC is applied (e.g., on each microphone signal using separate mono-AECs) is an application of mono-AECs.

Abstract: A call directing system receives an incoming call from a caller. The caller is prompted to speak, thus enabling a prosody analyzer to generate an analysis of a prosody of the caller's voice. This analysis provides a basis for generating a caller profile that describes caller preferences of the caller. Based on the analysis of the prosody of the caller's voice and the generated caller profile, the call is directed to a particular call recipient.

Abstract: Systems and methods for managing the volume of multiple VoIP streams are disclosed. The system includes a VoIP server configured to receive an input audio stream from a first VoIP handset, create separate output audio streams from the input audio stream for transmission to second and third VoIP handsets, and to connect to a communications network. The system also includes a volume control table coupled to the VoIP server, the volume control table including records of volume adjustments made during prior conversations between the two or more VoIP handsets. The VoIP server is further configured create the separate output audio streams such that one or more of the output streams has a volume that is different than input audio stream based on the records.

Abstract: A voice recognition system comprises: a voice input unit that receives an input signal from a voice input element and output it; a voice detection unit that detects an utterance segment in the input signal; a voice recognition unit that performs voice recognition for the utterance segment; and a control unit that outputs a control signal to at least one of the voice input unit and the voice detection unit and suppresses a detection frequency if the detection frequency satisfies a predetermined condition.

Abstract: A call directing system receives an incoming call from a caller. The caller is prompted to speak, thus enabling a prosody analyzer to generate an analysis of a prosody of the caller's voice. This analysis provides a basis for generating a caller profile that describes caller preferences of the caller. Based on the analysis of the prosody of the caller's voice and the generated caller profile, the call is directed to a particular call recipient.

Abstract: A communication apparatus through which voice communication can be performed, including: a line interface portion which receives and transmits data form and to a line and which includes a data access arrangement device in which is incorporated a detection circuit that detects at least one of a line voltage and a line current; a voice reproducing device which reproduces a voice that is based on voice communication data transmitted from the line to the line interface portion; and a volume adjuster which adjusts reproduction volume with which the voice is to be reproduced by the voice reproducing device, on the basis of a detected value of the detection circuit.

Abstract: In an information processing system provided with a camera and a microphone, for transmitting and receiving information of a user to and from another information processing system through a transmission line, image data of the user obtained by a camera is stored in a memory in advance. When one user communicates another user, image data of the one user is obtained by the camera and is synthesized with the image data stored in the memory in advance by image-processing. The clothes, hair, background, make-up etc. of the one user are made different to reality and the image data are transmitted to the another user in the communication.

Abstract: An apparatus to enable half-duplexing capabilities in a two-way communication device is disclosed. The apparatus estimates the signal power and background noise of a first input signal and a second input signal during approximately the same period. The apparatus further provides at least one control signal based on the result of one or more determinations. These determinations may include whether the estimated signal power of at least one of the first and second input signals exceeds a threshold value; whether the estimated signal power of the first input signal exceeds the sum of a first threshold value and the estimated background noise of the first input signal; and whether the estimated signal power of the second input signal exceeds the sum of a second threshold value and the estimated background noise of the second input signal. Other embodiments for use with two-way communication devices and related methods are also disclosed.

Abstract: A voice transmission device has a tandem pass through function in an STM, ATM, IP network, and a noise canceller (21) is provided at a latter stage of an echo canceller (12) in a coding part, and in a case where a multistage connection state does not occur, noise removal is performed to carry out efficient coding, and in a case where a relay is performed in the multistage connection state, switching is performed to stop the operation of the noise canceller (21), and voice deterioration by redundant decoding and coding is prevented, and therefore, even in a cellular phone having no noise cancel function, or the like, and at both a normal time and a time of a tandem pass through state, high quality voice transmission can be performed, and further, since an unvoiced portion in voice data is increased by removing a noise component, a portion subjected to coding becomes small, and transmission amount of the line is reduced.

Abstract: A telephone (310) and a method for providing outbound audio when the telephone is operating in a speakerphone mode. A first data unit (350) including a first unit type identifier (360) can be received by the telephone. The first unit type identifier can be an indicator of a type of audio data contained in the first data unit. For instance, the first unit type identifier can indicate whether the audio data is music or non-music audio data. If the first unit type identifier has a first value, for example a value indicating that the audio data is music data, unmuted outbound audio reproduced from the first data unit can be provided and voice activity detection can be disabled. Additionally, inbound audio can be muted.

Abstract: Communication terminals, methods, and computer program products are provided that sense background noise via a speaker that is also used to generate sounds. In some methods of operating a communication terminal, and a speaker signal is supplied to a first speaker to generate sound therefrom, a noise sensing signal is received from the first speaker. The noise sensing signal includes a contribution associated with background noise that is incident to the first speaker. Presence of the background noise in the noise sensing signal is determined.

Abstract: A system and method for adjusting the volume level of a communications device in response to a voice volume/ambient noise relationship. Ambient noise and voice volume are sampled and compared to a predetermined ambient noise to voice volume relationship. Voice volume is adjusted up or down in response to a control signal that is generated in view of the comparison between the sampled voice volume to ambient noise relationship and the predetermined ambient noise to voice volume relationship.

Abstract: A method is set forth of controlling an acoustic echo canceller at the output of a beamformer in an audio conferencing device. Information is saved to, and retrieved from, memory that characterizes each of a finite number of look directions, or regions of focus, covering the entire spatial span of the conferencing device. Each time a change occurs from a first look direction to a second look direction, information relating to the workspace captured by the acoustic echo canceller is saved for the first look direction, and previously saved information for the second look direction is retrieved from memory. The acoustic echo cancellation then takes place for the second look direction with the retrieved information.

Abstract: A plurality of Goertzel filters whose operating frequencies are distributed across the voice baseband are used to detect voice and control tones in a signal. Filters operating at frequencies of control tones and detecting that most of the signal energy occurs at those frequencies indicates presence of the control tones. At least three of the filters detecting that about 10% to 20% of the signal energy occurs at each of their operating frequencies indicate presence of voice. The total energy detected in the signal being below a noise threshold indicates presence of noise or silence.

Abstract: A method and apparatus for reducing echo feedback in a wireless communication system (10) is accomplished when a receiving communication unit (24) senses a feedback signal, or echo, via an ancillary communication path. The receiving communication unit is a targeted recipient of an original audio signal generated by a transmitting communication unit (22), where the original audio signal (42) is conveyed to the receiving communication unit. Upon detecting the feedback signal and determining that it exceeds a feedback threshold, the receiving communication unit attenuates an audible output of the original signal to reduce echo to the transmitting communication unit. In addition, the receiving communication unit, and/or the transmitting communication unit include echo canceller to further minimize the echo within the digital communication system.

Abstract: The present invention is directed to the provision of a personalized speaker phone and hands-free telephony. In particular, the present invention allows communications to be output along a narrowly defined path, rather than being broadcast. In this way, a private voice communication signal can be provided to a user, even though the user is not holding the output device to the user's ear. Furthermore, by providing audible signals along narrowly defined paths, different audible signals may be provided to users at the same location, without interfering with one another.

Abstract: Voice activity is detected by comparing a signal with two thresholds and producing data representing the energy of the signal. The data, in binary form, is compared with thresholds to determine voice activity. In accordance with another aspect of the invention, the thresholds are adjusted based upon statistical information. In accordance with another aspect of the invention, the data can be weighted to provide an indication of the quasi-RMS energy of an input signal. In accordance with another aspect of the invention, voice activity detectors, individually weighted, are provided at each input and each output of a telephone for reliably controlling echo cancelling circuitry within the telephone.

Abstract: The scope of the present invention is a device for detecting the source of a voice, which device comprises microphone means (2; 2a, 2b, 2M) for receiving a voice signal and detecting means for detecting the voice from the received voice signal. The device comprises means (15, 17) for determining the direction of arrival of the received signal, means (17) for storing the assumed direction of arrival of the voice of a certain source and means (18) for comparing the direction of arrival of said received signal with said assumed direction of arrival. The device further comprises means (18) for indicating that the source of the voice is said certain source when the comparison proves that the direction of arrival of said received signal matches with said assumed direction of arrival within a certain tolerance.

Abstract: A unique, fully integrated, fully programmable, and highly flexible sound distribution system and methodology for providing masking sound, background music, and paging capabilities in up to eight zones of a building or space is provided. The methodology embodied in the system includes internal masking sounds that are uniquely pre-filtered to provide efficient and effective masking of distracting sounds within selectable zones of the space with a minimum masking sound dB sound level and with a pleasant sounding and non-annoying masking sound. The system also incorporates the capacity to be controlled from a remote or local telephone to adjust the volume level in any zone serviced by the system by issuing appropriate DTMF codes from the telephone's keypad. Unique bi-tone diagnostic functions are provided for assuring that the entire system is correctly wired and installed and for troubleshooting operational anomalies.

Abstract: The invention relates to a mobile radio terminal including an audio transducer (5) an outlet (6) of which is oriented towards the front face of the terminal and provides earpiece, loudspeaker and ringer functions, the terminal further including, coupled to the transducer, means (R1, 9′, 11, 12) for adjusting the level of the sound wave emitted by the transducer in a main direction (D) substantially perpendicular to the front face, the adjustment being effected regardless of the position of the terminal relative to a user.

Abstract: A method for screening an active incoming voice mail message broadcasts the incoming message in real time on a speaker in or associated with the subscriber's telephone set upon and concurrent with receipt of the same by the voice mail system. Upon detection during the broadcast of an interrupt request provided by the subscriber via the subscriber's telephone set, the calling party is connected with the subscriber, and normal recording of the message by the voice mail system is discontinued.

Abstract: A method of displaying alternating transmitting and receiving phases of voice communication in a mobile phone with a display when it is operated in the speakerphone mode includes the steps of comparing the intensity of a received voice signal from a caller with that of a transmitted voice signal, outputting the received voice signal through the speaker of the mobile phone while displaying a visual indication representing the receiving phase on the display if the intensity of the received voice signal is stronger than that of the transmitted voice signal, and sending the transmitted voice signal to the caller while displaying a visual indication representing the transmitting phase on the display if the intensity of the received voice signal is weaker than that of the transmitted voice signal.

Abstract: Automatic assistance to unaided voice communication is provided by activating and deactivating a wireless communication link as needed (300). A communication device, associated with a particular individual, monitors to determine whether unaided communication occurring with another individual is satisfactory according to a predetermined criteria (310, 320, 330). The communication device automatically switches to provide aided communication, when the unaided communication is not satisfactory. Preferably, an open communication link is established between the communication device and one associated with the other individual when sound reception characteristics or separation characteristics do not meet a particular criteria (340, 350, 360, 370).