专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP4371113A1 APPARATUS, METHOD AND COMPUTER PROGRAM CODE FOR PROCESSING AUDIO STREAM 审中-公开
公开(公告)号：EP4371113A1
公开(公告)日：2024-05-22
申请号：EP22751014.6
申请日：2022-07-12
申请人： Utopia Music AG
发明人： WAHLGREN, Linus , FLACH, Max
IPC分类号： G10L25/54 , G10L25/18
CPC分类号： G10L25/54 , G10L25/18

2. 发明授权

EP3095117B1 MULTI-CHANNEL AUDIO SIGNAL CLASSIFIER 有权
公开(公告)号：EP3095117B1
公开(公告)日：2018-08-22
申请号：EP14877980.4
申请日：2014-01-13
申请人： Nokia Technologies Oy
发明人： VASILACHE, Adriana , LAAKSONEN, Lasse Juhani , RÄMÖ, Anssi Sakari
IPC分类号： G10L19/008 , H04S3/00 , G10L19/22 , G10L25/03
CPC分类号： G10L19/008 , G10L19/0204 , G10L19/035 , G10L19/22 , G10L25/03 , G10L25/18 , H04R2499/11 , H04S1/007 , H04S3/008 , H04S2420/01 , H04S2420/07
摘要： It is disclosed inter alia a method comprising: estimating a value of entropy for a multi-channel audio signal; determining a channel configuration of the multi-channel audio signal from the value of entropy; and encoding the multi-channel audio signal, wherein the mode of encoding is dependent on the channel configuration.

3. 发明公开

EP3332558A2 EVENT DETECTION FOR PLAYBACK MANAGEMENT IN AN AUDIO DEVICE 有权
公开(公告)号：EP3332558A2
公开(公告)日：2018-06-13
申请号：EP16763354.4
申请日：2016-08-05
申请人： Cirrus Logic International Semiconductor, Ltd.
发明人： EBENEZER, Samuel Von Parma
IPC分类号： H04S7/00 , G10L21/0272 , H04R1/10 , G10L25/78 , H04R3/00 , G10L21/0216
CPC分类号： G10L25/51 , G10L25/18 , G10L25/78 , G10L25/81 , G10L25/84 , G10L2021/02166 , G10L2025/783 , H04R1/1083 , H04R3/002 , H04R3/005 , H04R2410/05 , H04S7/00
摘要： In accordance with embodiments of the present disclosure, a method for processing audio information in an audio device may include reproducing audio information by generating an audio output signal for communication to at least one transducer of the audio device, receiving at least one input signal indicative of ambient sound external to the audio device, detecting from the at least one input signal a near-field sound in the ambient sound, and modifying a characteristic of the audio information reproduced to the at least one transducer in response to detection of the near-field sound.

4. 发明公开

EP3245652A4 DEPLOYED END-TO-END SPEECH RECOGNITION 有权
公开(公告)号：EP3245652A4
公开(公告)日：2018-05-30
申请号：EP16869294
申请日：2016-11-23
申请人： BAIDU USA LLC
发明人： CATANZARO BRYAN , CHEN JINGDONG , CHRZANOWSKI MIKE , ELSEN ERICH , ENGEL JESSE , FOUGNER CHRISTOPHER , HAN XU , HANNUN AWNI , PRENGER RYAN , SATHEESH SANJEEV , SENGUPTA SHUBHABRATA , YOGATAMA DANI , WANG CHONG , ZHAN JUN , ZHU ZHENYAO , AMODEI DARIO
IPC分类号： G10L15/16 , G10L15/06 , G10L15/08 , G10L15/183
CPC分类号： G10L15/16 , G06N3/0445 , G06N3/084 , G10L15/02 , G10L15/063 , G10L15/14 , G10L15/183 , G10L15/197 , G10L25/18 , G10L25/21 , G10L2015/0635
摘要： Embodiments of end-to-end deep learning systems and methods are disclosed to recognize speech of vastly different languages, such as English or Mandarin Chinese. In embodiments, the entire pipelines of hand-engineered components are replaced with neural networks, and the end-to-end learning allows handling a diverse variety of speech including noisy environments, accents, and different languages. Using a trained embodiment and an embodiment of a batch dispatch technique with GPUs in a data center, an end-to-end deep learning system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

5. 发明公开

EP3245597A4 END-TO-END SPEECH RECOGNITION 有权
公开(公告)号：EP3245597A4
公开(公告)日：2018-05-30
申请号：EP16869302
申请日：2016-11-23
申请人： BAIDU USA LLC
发明人： CATANZARO BRYAN , CHEN JINGDONG , CHRZANOWSKI MIKE , ELSEN ERICH , ENGEL JESSE , FOUGNER CHRISTOPHER , HAN XU , HANNUN AWNI , PRENGER RYAN , SATHEESH SANJEEV , SENGUPTA SHUBHABRATA , YOGATAMA DANI , WANG CHONG , ZHAN JUN , ZHU ZHENYAO , AMODEI DARIO
IPC分类号： G06F17/28 , G10L15/04 , G10L15/06 , G10L15/08 , G10L15/183 , G10L15/28
CPC分类号： G10L15/16 , G06N3/0445 , G06N3/084 , G10L15/02 , G10L15/063 , G10L15/14 , G10L15/183 , G10L15/197 , G10L25/18 , G10L25/21 , G10L2015/0635
摘要： Embodiments of end-to-end deep learning systems and methods are disclosed to recognize speech of vastly different languages, such as English or Mandarin Chinese. In embodiments, the entire pipelines of hand-engineered components are replaced with neural networks, and the end-to-end learning allows handling a diverse variety of speech including noisy environments, accents, and different languages. Using a trained embodiment and an embodiment of a batch dispatch technique with GPUs in a data center, an end-to-end deep learning system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

6. 发明公开

EP3306608A1 ESTIMATING AUDIBILITY OF AUDIO SAMPLES 审中-公开
标题翻译：估计音频样本的可听性
公开(公告)号：EP3306608A1
公开(公告)日：2018-04-11
申请号：EP16192913.8
申请日：2016-10-07
申请人： BMAT LICENSING, S.L.U.
发明人： MOLINA, Emilio , CANO, Pedro , CIURANA, Alex , LYDA, Johannes
IPC分类号： G10L25/69 , G10L25/18
CPC分类号： G10L25/18 , G10L25/69 , H03G5/005
摘要： Methods and devices for estimating audibility of audio samples in audio mixes of broadcast media programs are proposed. Example methods comprise the steps of providing a representation matrix of an audio mix, the audio mix comprising the audio sample and additional audio, providing a representation matrix of the audio sample, subtracting the representation matrix of the audio sample from representation matrix of the audio mix to generate a difference matrix, applying an audibility model to the difference matrix to generate an audibility matrix, determining an audibility level for each element of the audibility matrix, and averaging the determined audibility levels of the matrix to estimate the audibility of the audio sample.
摘要翻译：提出了用于估计广播媒体节目的音频混合中的音频样本的可听度的方法和设备。示例方法包括以下步骤：提供音频混合的表示矩阵，音频混合包括音频样本和附加音频;提供音频样本的表示矩阵;从音频混合的表示矩阵中减去音频样本的表示矩阵生成差异矩阵，将差异矩阵应用于差异矩阵以生成可听度矩阵，确定可听度矩阵的每个元素的可听度水平，以及平均矩阵的可确定可听度水平以估计音频样本的可听度。

7. 发明公开

EP3304547A1 SEPARATED AUDIO ANALYSIS AND PROCESSING 审中-实审
标题翻译：分离的音频分析和处理
公开(公告)号：EP3304547A1
公开(公告)日：2018-04-11
申请号：EP16729128.5
申请日：2016-05-26
申请人： Dolby Laboratories Licensing Corporation
发明人： SHI, Dong , SUN, Xuejing
IPC分类号： G10L21/02 , G10L25/48 , G10L25/18
CPC分类号： H04R3/04 , G06F3/165 , G10L21/02 , G10L21/0232 , G10L25/18 , G10L25/21 , G10L25/48 , H03G3/3005 , H03G5/025 , H03G5/165
摘要： Example embodiments disclosed herein relate to separated audio analysis and processing. A system for processing an audio signal is disclosed. The system includes an audio analysis module configured to analyze an input audio signal to determine a processing parameter for the input audio signal, the input audio signal being represented in time domain. The system also includes an audio processing module configured to process the input audio signal in parallel with the audio analysis module. The audio processing module includes a time domain filter configured to filter the input audio signal to obtain an output audio signal in the time domain, and a filter controller configured to control a filter coefficient of the time domain filter based on the processing parameter determined by the audio analysis module. Corresponding method and computer program product of processing an audio signal are also disclosed.

8. 发明公开

EP3282448A3 COMPRESSION OF DECOMPOSED REPRESENTATIONS OF A SOUND FIELD 审中-公开
公开(公告)号：EP3282448A3
公开(公告)日：2018-04-11
申请号：EP17177230.4
申请日：2014-05-29
申请人： Qualcomm Incorporated
发明人： Sen, Dipanjan , Ryu, Sang-Uk
IPC分类号： G10L19/038 , G10L19/008 , H04R5/00 , G06F17/16 , H04S7/00
CPC分类号： H04S5/005 , G06F17/16 , G10L19/002 , G10L19/008 , G10L19/0204 , G10L19/038 , G10L19/06 , G10L19/167 , G10L19/20 , G10L25/18 , G10L2019/0001 , G10L2019/0005 , H04R2205/021 , H04S7/30 , H04S7/304 , H04S7/40 , H04S2400/01 , H04S2400/15 , H04S2420/01 , H04S2420/03 , H04S2420/11
摘要： In general, techniques are described for performing a vector-based synthesis with respect to higher order ambisonic coefficients (or, in other words, spherical harmonic coefficients). A device comprising a processor may be configured to perform the techniques. The processor may perform the vector-based synthesis with respect to spherical harmonic coefficients to generate decomposed representations of the plurality of spherical harmonic coefficients and determine distinct and background directional information from the directional information. The processor may then reduce an order of the directional information associated with the background audio objects to generate transformed background directional information, and apply compensation to increase values of the transformed directional information to preserve an overall energy of the sound field.

9. 发明公开

EP3300079A1 SPEECH EVALUATION APPARATUS AND SPEECH EVALUATION METHOD 审中-公开
标题翻译：语音评估设备和语音评估方法
公开(公告)号：EP3300079A1
公开(公告)日：2018-03-28
申请号：EP17191059.9
申请日：2017-09-14
申请人： FUJITSU LIMITED
发明人： Otani, Takeshi , Togawa, Taro , Nakayama, Sayuri
IPC分类号： G10L25/90
CPC分类号： G10L25/60 , G10L21/0205 , G10L25/06 , G10L25/18 , G10L25/90 , G10L2025/906
摘要： The disclosed techniques intend to accurately determine the change amount of the fundamental pitch frequency even if distortion is generated in the voice waveform.
According to an aspect of the embodiments, a speech evaluation apparatus includes a memory, and a processor coupled to the memory and configured to generate a first input spectrum obtained by frequency transforming a first signal that is a signal of a first period, generate a second input spectrum obtained by frequency transforming a second signal that is the signal of a second period earlier than the first period, generate a processed spectrum obtained by transforming frequency of the second input spectrum based on a change ratio set in advance, calculate a correlation value between the first input spectrum and the processed spectrum, and determine a change amount of pitch frequency from the first signal to the second signal based on the change ratio and the correlation value.
摘要翻译：所公开的技术旨在即使在话音波形中产生失真，也准确地确定基本音调频率的变化量。根据实施例的一个方面，语音评估设备包括存储器和耦合到存储器并且被配置为生成通过对作为第一时段的信号的第一信号进行频率变换而获得的第一输入谱的处理器，生成第二输入谱通过频率变换作为比第一时段早的第二时段的信号的第二信号而获得的输入频谱，基于预先设置的变化比率来生成通过变换第二输入频谱的频率而获得的处理后的频谱，第一输入频谱和处理后的频谱，并且基于变化率和相关值来确定从第一信号到第二信号的音调频率的变化量。

10. 发明公开

EP3295456A1 AUDIO SOURCE SEPARATION WITH SOURCE DIRECTION DETERMINATION BASED ON ITERATIVE WEIGHTING 有权
公开(公告)号：EP3295456A1
公开(公告)日：2018-03-21
申请号：EP16736271
申请日：2016-05-12
申请人： DOLBY LABORATORIES LICENSING CORP
发明人： LU LIE , HU MINGQING
IPC分类号： G10L21/0272 , G10L25/18
CPC分类号： G10L21/0272 , G10L25/18
摘要： Example embodiments disclosed herein relate to audio source separation with source direction determined based on iterative weighted component analysis. A method of separating audio sources in audio content is disclosed. The audio content includes a plurality of channels. The method includes obtaining multiple data samples from multiple time-frequency tiles of the audio content. The method also includes analyzing the data samples to generate multiple components in a plurality of iterations, wherein each of the components indicates a direction with a variance of the data samples, and wherein in each of the plurality of iterations, each of the data samples is weighted with a weight that is determined based on a selected component from the multiple components. The method further includes determining a source direction of the audio content based on the selected component for separating an audio source from the audio content. Corresponding system and computer program product of separating audio sources in audio content are also disclosed.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式