-
1.发明公开
公开(公告)号：EP1450354A1
公开(公告)日：2004-08-25
申请号：EP04003811.9
申请日：2004-02-19
IPC分类号： G10L21/02
CPC分类号： G10L21/0232 , G10L21/0208 , G10L21/0264 , G10L2021/02163 , H04R2410/07
摘要： The invention includes a method, apparatus, and computer program to selectively suppress wind noise while preserving narrow-band signals in acoustic data. Sound from one or several microphones is digitized into binary data. A time-frequency transform is applied to the data to produce a series of spectra. The spectra are analyzed to detect the presence of wind noise and narrow band signals. Wind noise is selectively suppressed while preserving the narrow band signals. The narrow band signal is interpolated through the times and frequencies when it is masked by the wind noise. A time series is then synthesized from the signal spectral estimate that can be listened to. This invention overcomes prior art limitations that require more than one microphone and an independent measurement of wind speed. Its application results in good-quality speech from data severely degraded by wind noise.
摘要翻译： 本发明包括一种在声学数据中保留窄带信号的同时有选择地抑制风噪声的方法，装置和计算机程序。 来自一个或多个麦克风的声音被数字化为二进制数据。 时间 - 频率变换被应用于数据以产生一系列光谱。 分析频谱以检测风噪声和窄带信号的存在。 选择性地抑制风噪声，同时保持窄带信号。 当窄带信号被风噪声屏蔽时，该频带信号经过时间和频率被内插。 然后从可以收听的信号谱估计中合成时间序列。 本发明克服了现有技术的限制，其需要多于一个的麦克风和独立的风速测量。 其应用导致了风噪声严重恶化的数据的高质量语音。
-
公开(公告)号：EP1635329A3
公开(公告)日：2007-02-07
申请号：EP05022053.2
申请日：2000-08-29
发明人： Zakarauskas, Pierre
IPC分类号： G10L17/00
摘要： A system and method to identify a sound source among a group of sound sources. The invention matches the acoustic input to a number of signal models, one per source class, and produces a goodness-of-match number for each signal model. The sound source is declared to be of the same class as that of the signal model with the best goodness-of-match if that score is sufficiently high. The data are recorded with a microphone, digitized and transformed into the frequency domain. A signal detector is applied to the transient. A harmonic detection method can be used to determine if the sound source has harmonic characteristics. If at least some part of a transient contains signal of interest, the spectrum of the signal after resealing is compared to a set of signal models, and the input signal's parameters are fitted to the data. The average distortion is calculated to compare patterns with those of sources that used in training the signal models. Before classification can occur, a source model is trained with signal data. Each signal model is built by creating templates from input signal spectrograms when they are significantly different from existing templates. If an existing template is found that resembles the input pattern, the template is averaged with the pattern in such a way that the resulting template is the average of all the spectra that matched that template in the past.
-
公开(公告)号：EP1580730A3
公开(公告)日：2006-04-12
申请号：EP05006440.1
申请日：2005-03-23
IPC分类号： G10L21/02
CPC分类号： G10L21/0208 , G10L25/30
摘要： A speech signal isolation system configured to isolate and reconstruct a speech signal transmitted in an environment in which frequency components of the speech signal are masked by background noise. The speech signal isolation system obtains a noisy speech signal from an audio source. The noisy speech signal may then be fed through a neural network that has been trained to isolate and reconstruct a clean speech signal from against background noise. Once the noisy speech signal has been fed through the neural network, the speech signal isolation system generates an estimated speech signal with substantially reduced noise.
-
公开(公告)号：EP1450354B1
公开(公告)日：2006-06-21
申请号：EP04003811.9
申请日：2004-02-19
IPC分类号： G10L21/02
CPC分类号： G10L21/0232 , G10L21/0208 , G10L21/0264 , G10L2021/02163 , H04R2410/07
摘要： The invention includes a method, apparatus, and computer program to selectively suppress wind noise while preserving narrow-band signals in acoustic data. Sound from one or several microphones is digitized into binary data. A time-frequency transform is applied to the data to produce a series of spectra. The spectra are analyzed to detect the presence of wind noise and narrow band signals. Wind noise is selectively suppressed while preserving the narrow band signals. The narrow band signal is interpolated through the times and frequencies when it is masked by the wind noise. A time series is then synthesized from the signal spectral estimate that can be listened to. This invention overcomes prior art limitations that require more than one microphone and an independent measurement of wind speed. Its application results in good-quality speech from data severely degraded by wind noise.
-
5.发明公开Isolating speech signals utilizing neural networks 有权Terennung von Sprachsignalen unter Verwendung von neuronalen Netzen
公开(公告)号：EP1580730A2
公开(公告)日：2005-09-28
申请号：EP05006440.1
申请日：2005-03-23
CPC分类号： G10L21/0208 , G10L25/30
摘要： A speech signal isolation system configured to isolate and reconstruct a speech signal transmitted in an environment in which frequency components of the speech signal are masked by background noise. The speech signal isolation system obtains a noisy speech signal from an audio source. The noisy speech signal may then be fed through a neural network that has been trained to isolate and reconstruct a clean speech signal from against background noise. Once the noisy speech signal has been fed through the neural network, the speech signal isolation system generates an estimated speech signal with substantially reduced noise.
摘要翻译： 一种语音信号隔离系统，被配置为隔离和重构在其中语音信号的频率分量被背景噪声屏蔽的环境中发送的语音信号。 语音信号隔离系统从音频源获得有噪声的语音信号。 然后可以通过经过训练的神经网络馈送噪声语音信号，以隔离和重建来自背景噪声的干净的语音信号。 一旦噪声语音信号已通过神经网络馈送，则语音信号隔离系统产生具有显着降低的噪声的估计语音信号。
-
公开(公告)号：EP1450353A1
公开(公告)日：2004-08-25
申请号：EP04003675.8
申请日：2004-02-18
IPC分类号： G10L21/02
CPC分类号： G10L21/0208 , G10L21/0232
摘要： A voice enhancement logic improves the perceptual quality of a processed voice. The voice enhancement system includes a noise detector and a noise attenuator. The noise detector detects a wind buffet and a continuous noise by modeling the wind buffet. The noise attenuator dampens the wind buffet to improve the intelligibility of an unvoiced, a fully voiced, or a mixed voice segment.
摘要翻译： 语音增强逻辑提高了处理语音的感知质量。 语音增强系统包括噪声检测器和噪声衰减器。 噪音检测器通过对风自助餐进行建模来检测风自助餐和持续的噪音。 噪音衰减器抑制风自助餐，以提高清音，完全声音或混合声音段的清晰度。
-
公开(公告)号：EP1450353B1
公开(公告)日：2006-08-02
申请号：EP04003675.8
申请日：2004-02-18
IPC分类号： G10L21/02
CPC分类号： G10L21/0208 , G10L21/0232
-
8.发明公开System, method and program for sound source classification 审中-公开System，Verfahren und Programm zur Klassifizierung von Schallquellen
公开(公告)号：EP1635329A2
公开(公告)日：2006-03-15
申请号：EP05022053.2
申请日：2000-08-29
发明人： Zakarauskas, Pierre
IPC分类号： G10L17/00
摘要： A system and method to identify a sound source among a group of sound sources. The invention matches the acoustic input to a number of signal models, one per source class, and produces a goodness-of-match number for each signal model. The sound source is declared to be of the same class as that of the signal model with the best goodness-of-match if that score is sufficiently high. The data are recorded with a microphone, digitized and transformed into the frequency domain. A signal detector is applied to the transient. A harmonic detection method can be used to determine if the sound source has harmonic characteristics. If at least some part of a transient contains signal of interest, the spectrum of the signal after resealing is compared to a set of signal models, and the input signal's parameters are fitted to the data. The average distortion is calculated to compare patterns with those of sources that used in training the signal models. Before classification can occur, a source model is trained with signal data. Each signal model is built by creating templates from input signal spectrograms when they are significantly different from existing templates. If an existing template is found that resembles the input pattern, the template is averaged with the pattern in such a way that the resulting template is the average of all the spectra that matched that template in the past.
摘要翻译： 一组识别声源的声源的系统和方法。 本发明将声输入匹配到多个信号模型，每个源类别一个信号模型，并且为每个信号模型产生一个良好的匹配次数。 如果该分数足够高，则声源被声明为具有最佳匹配度的信号模型的声源。 用麦克风记录数据，数字化并变换到频域。 信号检测器应用于瞬态。 可以使用谐波检测方法来确定声源是否具有谐波特性。 如果瞬变的至少部分包含感兴趣的信号，则将再密封后的信号的频谱与一组信号模型进行比较，并将输入信号的参数拟合到数据中。 计算平均失真以将模式与用于训练信号模型的源的模式进行比较。 在分类之前，可以用信号数据对源模型进行训练。 每个信号模型是通过从输入信号谱图创建模板构建的，当它们与现有模板显着不同时。 如果找到类似于输入模式的现有模板，则模板将以该模式进行平均，使得所得到的模板是与过去匹配该模板的所有光谱的平均值。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.014 秒)
