-
公开(公告)号：US11488613B2
公开(公告)日：2022-11-01
申请号：US17098090
申请日：2020-11-13
发明人： Minje Kim , Kai Zhen , Mi Suk Lee , Seung Kwon Beack , Jongmo Sung , Tae Jin Lee , Jin Soo Choi
IPC分类号： G10L19/08 , G10L19/032 , G10L19/26 , G06N3/08 , G10L25/30 , G10L13/02 , G10L21/0208
摘要： Disclosed are a method for coding a residual signal of LPC coefficients based on collaborative quantization and a computing device for performing the method. The residual signal coding method includes: generating encoded LPC coefficients and LPC residual signals by performing LPC analysis and quantization on an input speech; Determining a predicted LPC residual signal by applying the LPC residual signal to cross module residual learning; Performing LPC synthesis using the coded LPC coefficients and the predicted LPC residual signal; It may include the step of determining an output speech that is a synthesized output according to a result of performing the LPC synthesis.
-
公开(公告)号：US11276413B2
公开(公告)日：2022-03-15
申请号：US16543095
申请日：2019-08-16
发明人： Mi Suk Lee , Jongmo Sung , Minje Kim , Kai Zhen
摘要： Disclosed are an audio signal encoding method and audio signal decoding method, and an encoder and decoder performing the same. The audio signal encoding method includes applying an audio signal to a training model including N autoencoders provided in a cascade structure, encoding an output result derived through the training model, and generating a bitstream with respect to the audio signal based on the encoded output result.
-
3.发明授权公开(公告)号：US11837220B2
公开(公告)日：2023-12-05
申请号：US17308800
申请日：2021-05-05
发明人： Minje Kim , Mi Suk Lee , Seung Kwon Beack , Jongmo Sung , Tae Jin Lee , Jin Soo Choi , Kai Zhen
摘要： Disclosed is a speech processing apparatus and method using a densely connected hybrid neural network. The speech processing method includes inputting a time domain sample of N*1 dimension for an input speech into a densely connected hybrid network; passing the time domain sample through a plurality of dense blocks in a densely connected hybrid network; reshaping the time domain samples into M subframes by passing the time domain samples through the plurality of dense blocks; inputting the M subframes into gated recurrent unit (GRU) components of N/M-dimension; outputting clean speech from which noise is removed from the input speech by passing the M subframes through GRU components.
-
公开(公告)号：US11790926B2
公开(公告)日：2023-10-17
申请号：US17156006
申请日：2021-01-22
发明人： Mi Suk Lee , Seung Kwon Beack , Jongmo Sung , Tae Jin Lee , Jin Soo Choi , Minje Kim , Kai Zhen
IPC分类号： G10L19/038 , G10L19/028 , G10L25/18 , G10L25/21 , G10L25/30
CPC分类号： G10L19/038 , G10L19/028 , G10L25/18 , G10L25/21 , G10L25/30
摘要： A method and apparatus for processing an audio signal are disclosed. According to an example embodiment, a method of processing an audio signal may include acquiring a final audio signal for an initial audio signal using a plurality of neural network models generating output audio signals by encoding and decoding input audio signals, calculating a difference between the initial audio signal and the final audio signal in a time domain, converting the initial audio signal and the final audio signal into Mel-spectra, calculating a difference between the Mel-spectra of the initial audio signal and the final audio signal in a frequency domain, training the plurality of neural network models based on results calculated in the time domain and the frequency domain, and generating a new final audio signal distinguished from the final audio signal from the initial audio signal using the trained neural network models.
-
公开(公告)号：US11664037B2
公开(公告)日：2023-05-30
申请号：US17326035
申请日：2021-05-20
发明人： Woo-taek Lim , Seung Kwon Beack , Jongmo Sung , Mi Suk Lee , Tae Jin Lee , Inseon Jang , Minje Kim , Haici Yang
IPC分类号： G10L19/032 , G10L21/0272
CPC分类号： G10L19/032 , G10L21/0272
摘要： Methods of encoding and decoding a speech signal using a neural network model that recognizes sound sources, and encoding and decoding apparatuses for performing the methods are provided. A method of encoding a speech signal includes identifying an input signal for a plurality of sound sources; generating a latent signal by encoding the input signal; obtaining a plurality of sound source signals by separating the latent signal for each of the plurality of sound sources; determining a number of bits used for quantization of each of the plurality of sound source signals according to a type of each of the plurality of sound sources; quantizing each of the plurality of sound source signals based on the determined number of bits; and generating a bitstream by combining the plurality of quantized sound source signals.
-
公开(公告)号：US20180144757A1
公开(公告)日：2018-05-24
申请号：US15820852
申请日：2017-11-22
发明人： Seung Kwon Beack , Jongmo Sung , Mi Suk Lee , Young Ho Jeong , Tae Jin Lee , Sang Won Suh
CPC分类号： G10L19/167 , G06F17/2252
摘要： Disclosed is a bitstream generation method performed by an acoustic data transmission (ADT) encoder, the method including receiving a first audio signal, receiving additional information converted into a bitstream, and transmitting a second audio signal obtained by inserting the bitstream into the first audio signal, to an ADT decoder.
-
公开(公告)号：US09407871B2
公开(公告)日：2016-08-02
申请号：US14625962
申请日：2015-02-19
发明人： Mi Suk Lee , In Ki Hwang
CPC分类号： H04N7/15 , G06F3/013 , G06F3/017 , G06F3/0304 , G06K9/00335 , G06K9/00597 , G06T3/0093 , H04N7/144 , H04N7/147
摘要： Disclosed are an apparatus and a method of controlling an eye-to-eye contact function, which provide a natural eye-to-eye contact by controlling an eye-to-eye contact function based on gaze information about a local participant and position information about a remote participant on a screen when providing the eye-to-eye contact function by using an image combination method and the like in a teleconference system, thereby improving absorption to a teleconference.
摘要翻译： 公开了一种控制眼睛接触功能的装置和方法，其通过基于关于本地参与者的凝视信息和关于本地参与者的位置信息来控制眼睛接触功能来提供自然的眼睛接触接触 通过在电话会议系统中使用图像组合方法等来提供眼睛接触功能，从而提高对电话会议的吸收的屏幕上的远程参与者。
-
公开(公告)号：US11508385B2
公开(公告)日：2022-11-22
申请号：US16686859
申请日：2019-11-18
发明人： Seung Kwon Beack , Jongmo Sung , Mi Suk Lee , Tae Jin Lee , Hui Yong Kim
IPC分类号： G06N3/04 , G06N3/08 , G10L19/032 , G10L19/02
摘要： Disclosed is a method of processing a residual signal for audio coding and an audio coding apparatus. The method learns a feature map of a reference signal through a residual signal learning engine including a convolutional layer and a neural network and performs learning based on a result obtained by mapping a node of an output layer of the neural network and a quantization level of index of the residual signal.
-
9.发明申请公开(公告)号：US20220020385A1
公开(公告)日：2022-01-20
申请号：US17377157
申请日：2021-07-15
发明人： Seung Kwon Beack , Jongmo Sung , Mi Suk Lee , Tae Jin Lee , Woo-taek Lim , Inseon Jang , Jin Soo Choi
IPC分类号： G10L19/06 , G10L19/032
摘要： An audio signal encoding method performed by an encoder includes identifying a time-domain audio signal in a unit of blocks, quantizing a linear prediction coefficient extracted from a combined block in which a current original block of the audio signal and a previous original block chronologically adjacent to the current original block using frequency-domain linear predictive coding (LPC), generating a temporal envelope by dequantizing the quantized linear prediction coefficient, extracting a residual signal from the combined block based on the temporal envelope, quantizing the residual signal by one of time-domain quantization and frequency-domain quantization, and transforming the quantized residual signal and the quantized linear prediction coefficient into a bitstream.
-
公开(公告)号：US20210005208A1
公开(公告)日：2021-01-07
申请号：US16686859
申请日：2019-11-18
发明人： Seung Kwon Beack , Jongmo Sung , Mi Suk Lee , Tae Jin Lee , Hui Yong Kim
IPC分类号： G10L19/02 , G10L19/032 , G06N3/08 , G06N3/04
摘要： Disclosed is a method of processing a residual signal for audio coding and an audio coding apparatus. The method learns a feature map of a reference signal through a residual signal learning engine including a convolutional layer and a neural network and performs learning based on a result obtained by mapping a node of an output layer of the neural network and a quantization level of index of the residual signal.
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.02 秒)
