Abstract: Disclosed is a noise suppression system including a unit for calculating a noise mean spectrum from an input signal, a unit for deriving the provisional estimate speech from the input signal and the noise mean spectrum, a reference speech pattern, and a unit for correcting the provisional estimate speech using the reference pattern.

Abstract: To remove only noise components without removing desired signal components, a signal processing apparatus includes a noise decorrelator that removes noise signals having correlation between at least two input signals, in each of which a desired signal and a noise signal coexist, by receiving the at least two input signals from at least two channels, and a residual noise remover that removes residual noise included in an output signal of the noise decorrelator based on a phase difference between the output signal of the noise decorrelator and at least one input signal included in the at least two input signals.

Abstract: A speech detection device according to the present invention acquires an acoustic signal, calculates a feature value representing a spectrum shape for a plurality of first frames from the acoustic signal, calculates a ratio of a likelihood of a voice model to a likelihood of a non-voice model for the first frames using the feature value, determines a candidate target voice section that is a section including target voice by use of the likelihood ratio, calculates a posterior probability of a plurality of phonemes using the feature value, calculates at least one of entropy and time difference of posterior probabilities of the plurality of phonemes for the first frames, and specifies a section as changed to a section not including the target voice, out of the candidate target voice sections, by use of at least one of the entropy and the time difference of the posterior probabilities.

Abstract: Provided are a noise reduction system that highly precisely estimates noise contained in an input signal and highly precisely reduces the noise contained in the input signal using the estimated noise, a speech detection system, a speech recognition system, a noise reduction method, and a noise reduction program.

Abstract: A speech detection device according to the present invention acquires an acoustic signal, calculates a sound level for first frames in the acoustic signal, determines the first frame having the sound level greater than or equal to a first threshold value as a first target frame, calculates a feature value representing a spectrum shape for second frames in the acoustic signal, calculates a ratio of a likelihood of a voice model to a likelihood of a non-voice model for the second frames with the feature value as an input, determines the second frame having the likelihood ratio greater than or equal to a second threshold value as a second target frame, and determines a section included in both a first target section corresponding to the first target frame and a second target section corresponding to the second target frame as a target voice section including the target voice.

Abstract: A speech processing system placed in a vehicle to effectively acquire a voice of a driver includes a first microphone that is provided on a surface facing the driver of the vehicle out of a steering wheel of the vehicle, and inputs a voice of the driver, a second microphone that is provided at a position where the voice of the driver of the vehicle is blocked by at least part of the steering wheel in the vehicle, and inputs noise in the vehicle, and a noise suppressor that suppresses an estimated noise signal based on a first signal corresponding to the sound input to the first microphone and a second signal corresponding to the sound input to the second microphone, and generates and outputs a pseudo speech signal.

Abstract: A voice separation means 82 separates an input voice of a volume adjusted by an input volume adjustment means 81, into a voice recognition voice and a monitoring voice. A monitoring volume adjustment means 83 adjusts a volume of the monitoring voice. An output volume adjustment means 84 adjusts a volume of an output voice and causes an output device to output the output voice of the adjusted volume, the output voice being a voice obtained by synthesizing a synthetic voice and the monitoring voice of the volume adjusted by the monitoring volume adjustment means 83, the synthetic voice being a voice synthesized from information generated as a result of voice recognition of the voice recognition voice. A control means 85 instructs the monitoring volume adjustment means 83 to adjust the volume of the monitoring voice so that an amplification factor of the volume of the output voice with respect to the volume of the input voice does not exceed 1.

Abstract: A system of this invention is directed to a speech processing system that efficiently performs noise suppression processing for a plurality of noise sources spreading in a lateral direction with respect to a speaker of interest.

Abstract: To input the voice of the passenger of a vehicle and output a piece of high-quality enhanced speech independently of the direction of a piece of speech or noise, a speech processing apparatus includes a first microphone that is provided on one of a ceiling member in a vehicle and an accessary thereof, inputs a sound mixture including a voice of a passenger of the vehicle and noise in the vehicle, and outputs a first signal, a second microphone that is provided on one of the ceiling member in the vehicle and the accessary thereof at a position farther than the first microphone when viewed from the passenger of the vehicle, inputs the noise in the vehicle while insulating the voice of the passenger of the vehicle using one of the ceiling member of the vehicle and the accessory thereof, and outputs a second signal, and a noise suppressor that outputs an enhanced speech signal based on the first signal and the second signal.

Abstract: An apparatus of this invention is directed to a speech input apparatus for obtaining a piece of high-quality speech with included noise reduced. The speech input apparatus includes a sound insulating block attached to a ceiling member in a vehicle, a first microphone that is attached to a side surface of the sound insulating block or the ceiling member in the vicinity of the sound insulating block on a side close to a passenger of the vehicle, inputs a sound mixture including the voice of the passenger and noise in the vehicle, and outputs a first signal to a noise suppressor configured to output an enhanced speech signal, and a second microphone that is attached to a side surface of the sound insulating block or the ceiling member in the vicinity of the sound insulating block on a side far from the passenger, inputs the noise in the vehicle, and outputs a second signal to the noise suppressor.

Abstract: Provided are a noise reduction system that highly precisely estimates noise contained in an input signal and highly precisely reduces the noise contained in the input signal using the estimated noise, a speech detection system, a speech recognition system, a noise reduction method, and a noise reduction program.

Abstract: A method for processing multichannel acoustic signals which is characterized by calculating the feature quantity of each channel from the input signals of a plurality of channels, calculating similarity between the channels in the feature quantity of each channel, selecting channels having high similarity, and separating signals using the input signals of the selected channels.

Abstract: A method for processing multichannel acoustic signals which processes input signals of a plurality of channels including the voices of a plurality of speaking persons. The method is characterized by detecting the voice section of each speaking person or each channel, detecting overlapped sections wherein the detected voice sections are common between channels, determining a channel to be subjected to crosstalk removal and the section thereof by use of at least voice sections not including the detected overlapped sections, and removing crosstalk in the sections of the channel to be subjected to the crosstalk removal.

Abstract: A method for processing multichannel acoustic signals, whereby input signals of a plurality of channels including the voices of a plurality of speaking persons are processed. The method is characterized by comprising: calculating the first feature quantity of the input signals of the multichannels for each channel; calculating similarity of the first feature quantity of each channel between the channels; selecting channels having high similarity; separating signals using the input signals of the selected channels; inputting the input signals of the channels having low similarity and the signals after the signal separation; and detecting a voice section of each speaking person or each channel.

Abstract: A frame extracting means 71 extracts frames from sample data as voice data in which whether each frame is an active voice frame or a non-active voice frame is already known. A feature quantity calculating means 72 calculates multiple feature quantities of each of the frames. A feature quantity integrating means 73 calculates an integrated feature quantity of the multiple feature quantities. A judgment means 74 judges whether each of the frames is an active voice frame or a non-active voice frame. An erroneous feature quantity calculation value calculating means 75 obtains a first erroneous feature quantity calculation value and a second erroneous feature quantity calculation value by executing prescribed calculations. A weight updating means 76 updates weights used for weighting so that the rate between the first erroneous feature quantity calculation value and the second erroneous feature quantity calculation value approaches a prescribed value.

Abstract: A voice separation means 82 separates an input voice of a volume adjusted by an input volume adjustment means 81, into a voice recognition voice and a monitoring voice. A monitoring volume adjustment means 83 adjusts a volume of the monitoring voice. An output volume adjustment means 84 adjusts a volume of an output voice and causes an output device to output the output voice of the adjusted volume, the output voice being a voice obtained by synthesizing a synthetic voice and the monitoring voice of the volume adjusted by the monitoring volume adjustment means 83, the synthetic voice being a voice synthesized from information generated as a result of voice recognition of the voice recognition voice. A control means 85 instructs the monitoring volume adjustment means 83 to adjust the volume of the monitoring voice so that an amplification factor of the volume of the output voice with respect to the volume of the input voice does not exceed 1.

Abstract: A speech sound detection apparatus receives an input audio signal (as a sound reception unit), and computes input power that indicates a magnitude of the sound represented by the audio signal (as an input power computation unit). The apparatus estimates a correction function that is a continuous function defining a relation between a certain frequency and a correction coefficient used to approximate the input power computed at that frequency to the reference power predetermined for that frequency (as a correction function estimation unit). The apparatus corrects the input power at every frequency, based upon the correction coefficient that is obtained in accordance with the relation defined by the estimated correction function (as an input power correcting unit). The apparatus further determines whether or not the sound represented by the received audio signal is speech sound, based upon the corrected input power (as a speech sound detection unit).

Abstract: A signal correction apparatus receives an input audio signal (serving as a first sound reception means). The signal correction apparatus computes, at every frequency, first power that indicates magnitude of sound represented by the input audio signal (serving as a first power computation means). The signal correction apparatus estimates a correction function that is a continuous function defining a relation between each frequency and a correction coefficient used to approximate the first power computed at that frequency to the reference power predetermined for that frequency (serving as a correction function estimation means). The signal correction apparatus multiplies the computed first power by the correction coefficient acquired in accordance with the relation defined by the estimated correction function so as to correct the first power at every frequency (serving as a power correcting means).

Abstract: Judgment result deriving means 74 makes a judgment between active voice and non-active voice every unit time for a time series of voice data in which the number of active voice segments and the number of non-active voice segments are already known as a number of the labeled active voice segment and a number of the labeled non-active voice segment and shapes active voice segments and non-active voice segments as the result of the judgment by comparing the length of each segment during which the voice data is consecutively judged to correspond to active voice by the judgment or the length of each segment during which the voice data is consecutively judged to correspond to non-active voice by the judgment with a duration threshold. Segments number calculating means 75 calculates the number of active voice segments and the number of non-active voice segments.

Abstract: A system for voice detection includes a feature value calculation unit that calculates a feature value from an input signal sliced on a per frame basis, a provisional voice/non-voice decision unit that provisionally decides a voiced interval and a non-voiced interval from the feature value calculated on a per frame basis, and a voice/non-voice decision unit that determines a voiced interval duration threshold value or a non-voiced interval duration threshold value, using a ratio of the feature value found on a per frame basis to a threshold value for the feature value and that re-decides the voiced interval and the non-voiced interval, using the voiced interval duration threshold value determined and the non-voiced interval duration threshold value determined.