Tencent Technology (shenzhen) Company Limited

Aac Optics (changzhou) Co., Ltd.

Changzhou Raytech Optronics Co., Ltd.

Dong Yu

Dan Su

Jun Wang

Yun Yang

Jiaqi Pan

Yanan Wang

Wanxia Li

Yong Xu

Zefeng Yang

Shiyin Kang

Lianwu Chen

Meng Yu

Mu Wang

Wingyip Lam

Shixiong Zhang

Wing Yip Lam

Ying Deng

Weixiang Yu

Rongzhi Gu

Xixin Wu

Qingbo Yu

Linying Xie

A method includes displaying a virtual map of a virtual environment including an identification of a first virtual object and an identification of a second virtual object in the virtual environment, and displaying a hot zone display element on the virtual map in response to a determination that the first virtual object interacts with the second virtual object. The hot zone display element indicates a map area in which the first virtual object interacts with the second virtual object. The method further includes displaying a visual field picture of the virtual environment from a perspective of the first virtual object or the second virtual object in response to a trigger operation on the hot zone display element.

Displaying visual field picture based on interaction zone on a virtual map

A method of training an audio separation network is provided. The method includes obtaining a first separation sample set, the first separation sample set including at least two types of audio with dummy labels, obtaining a first sample set by performing interpolation on the first separation sample set based on perturbation data, obtaining a second separation sample set by separating the first sample set using an unsupervised network, determining losses of second separation samples in the second separation sample set, and adjusting network parameters of the unsupervised network based on the losses of the second separation samples, such that a first loss of a first separation result outputted by an adjusted unsupervised network meets a convergence condition.

Training method and device for audio separation network, audio separation method and device, and medium

This application relates to a speech synthesis method and apparatus, a model training method and apparatus, and a computer device. The method includes: obtaining to-be-processed linguistic data; encoding the linguistic data, to obtain encoded linguistic data; obtaining an embedded vector for speech feature conversion, the embedded vector being generated according to a residual between synthesized reference speech data and reference speech data that correspond to the same reference linguistic data; and decoding the encoded linguistic data according to the embedded vector, to obtain target synthesized speech data on which the speech feature conversion is performed. The solution provided in this application can prevent quality of a synthesized speech from being affected by a semantic feature in a mel-frequency cepstrum.

Voice synthesis method, model training method, device and computer device

This application relates to a method of extracting an inter channel feature from a multi-channel multi-sound source mixed audio signal performed at a computing device. The method includes: transforming one channel component of a multi-channel multi-sound source mixed audio signal into a single-channel multi-sound source mixed audio representation in a feature space; performing a two-dimensional dilated convolution on the multi-channel multi-sound source mixed audio signal to extract inter-channel features; performing a feature fusion on the single-channel multi-sound source mixed audio representation and the inter-channel features; estimating respective weights of sound sources in the single-channel multi-sound source mixed audio representation based on a fused multi-channel multi-sound source mixed audio feature; obtaining respective representations of the plurality of sound sources according to the single-channel multi-sound source mixed audio representation and the respective weights; and transforming the respective representations of the sound sources into respective audio signals of the plurality of sound sources.

Inter-channel feature extraction method, audio separation method and apparatus, and computing device

A speech separation model training method and apparatus, a computer-readable storage medium, and a computer device are provided, the method including: obtaining first audio and second audio, the first audio including target audio and having corresponding labeled audio, and the second audio including noise audio. obtaining an encoding model, an extraction model, and an initial estimation model; performing unsupervised training on the encoding model, the extraction model, and the estimation model according to the second audio, and adjusting model parameters of the extraction model and the estimation model; performing supervised training on the encoding model and the extraction model according to the first audio and the labeled audio corresponding to the first audio, and adjusting a model parameter of the encoding model; continuously performing the unsupervised training and the supervised training, so that the unsupervised training and the supervised training overlap, and the training is not finished until a training stop condition is met.

Speech separation model training method and apparatus, storage medium and computer device

The present disclosure relates to optical lens, and provides a camera optical lens including from an object side to an image side in sequence: a first lens having a positive refractive power, a second lens, a third lens, a fourth lens, a fifth lens, a sixth lens, a seventh lens, and an eighth lens; wherein the camera optical lens satisfies the following conditions: 0.95≤f/TTL; −4.00≤f2/f≤−1.90; and 0.25≤(R15+R16)/(R15−R16)≤0.90. The camera optical lens can achieve good optical performance while meeting design requirements for a long focal length and ultra-thinness.

Camera optical lens

A camera optical lens includes a first lens having a positive refractive power, a second lens having a refractive power, a third lens having a negative refractive power, a fourth lens having a positive refractive power, and a fifth lens having a negative refractive power, which are sequentially arranged from an object side to an image side. 0.90&#x2264;f1/f&#x2264;1.20, 5.00&#x2264;(R3+R4)/(R3&#x2212;R4)&#x2264;30.00, 3.00&#x2264;d5/d6&#x2264;10.00, and &#x2212;15.00&#x2264;(R5+R6)/(R5&#x2212;R6)&#x2264;&#x2212;3.00. f denotes a focal length of the camera optical lens, f1 denotes a focal length of the first lens, R3 denotes a curvature radius of an object-side surface of the second lens, R4 denotes a curvature radius of an image-side surface of the second lens, and R5 denotes a curvature radius of an object-side surface of the third lens. The camera optical lens has good optical performance and meets the design requirements of a large aperture, a wide angle, and ultra-thinness.

A camera optical lens is provided. The camera optical lens includes, from an object side to an image side, a first lens, a second lens having a negative refractive power, a third lens, a fourth lens, a fifth lens, a sixth lens, a seventh lens, an eighth lens, and a ninth lens. The camera optical lens satisfies following conditions: 2.00&#x2264;f1/f&#x2264;5.50; and 2.00&#x2264;d7/d8&#x2264;10.00, where f denotes a focal length of the camera optical lens, f1 denotes a focal length of the first lens, d7 denotes an on-axis thickness of the fourth lens, and d8 denotes an on-axis distance from an image side surface of the fourth lens to an object side surface of the fifth lens. The camera optical lens according to the present disclosure satisfies design requirements for large-aperture, wide-angle, and ultra-thin lenses while achieving good optical performance.

A camera optical lens includes first to fifth lenses from an object side to an image side, which are first and fourth lenses having positive refractive power, and second, third and fifth lenses having negative refractive power. The camera optical lens satisfies 0.90&#x2264;f1/f&#x2264;1.30; &#x2212;5.00&#x2264;f3/f&#x2264;&#x2212;2.50; 10.00&#x2264;d1/d2&#x2264;25.00; and 0&#x2264;(R7+R8)/(R7&#x2212;R8)&#x2264;0.90, where f, f1 and f3 respectively denote focal lengths of the camera optical lens, the first lens, and the third lens, R7 denotes a curvature radius of an object side surface of the fourth lens, R8 denotes a curvature radius of an image side surface of the fourth lens, d1 denotes an on-axis thickness of the first lens, and d2 denotes an on-axis distance from an image side surface of the first lens to an object side surface of the second lens. The camera optical lens has good optical performance and satisfies design requirements of a large angle, a wide angle and ultra-thinness.

A camera optical lens includes first to fourth lenses from an object side to an image side, with first and fourth lenses having negative refractive power, and a third lens having positive refractive power, and satisfies &#x2212;3.50&#x2264;f1/f&#x2264;&#x2212;2.00; 0.55&#x2264;f3/f&#x2264;0.75; 5.00&#x2264;d3/d4&#x2264;15.00; 5.00&#x2264;d5/d6&#x2264;35.00; &#x2212;20.00&#x2264;(R3+R4)/(R3&#x2212;R4)&#x2264;&#x2212;3.00; and &#x2212;5.00&#x2264;R1/R2&#x2264;&#x2212;2.00, where f, f1, and f3 respectively denote focal lengths of the camera optical lens, the first lens, and the third lens, d3 and d5 respectively denote on-axis thicknesses of second and third lenses, d4 and d6 respectively denote a distance between second and third lenses and a distance between third and fourth lenses, R3 and R4 respectively denote curvature radii of object side and image side surfaces of the second lens, and R1 and R2 denotes curvature radii of object side and image side surfaces of the first lens, thereby having good optical performance while meeting design requirements of a wide angle and ultra-thinness.

Growing community of inventors

Shenzhen, China

Dong Yu