95 results about "Mean opinion score" patented technology

A method is provided for optimizing an objective measure used to estimate mean opinion score or naturalness of synthesized speech from a speech synthesizer. The method includes using an objective measure that has components derived directly from textual information used to form synthesized utterances. The objective measure has a high correlation with mean opinion score such that a relationship can be formed between the objective measure and corresponding mean opinion score. The objective measure is altered to provide a different function of textual information derived from the utterances so as to improve the relationship between the scores of the objective measure and subjective ratings of the synthesized utterances.

A method and system for the estimation of the effect of packet loss on a viewer's subjective perception of a packet video stream. The method involves estimating a quality metric for every frame in the video stream, accumulating such metrics over time, and transforming the result into a Mean Opinion Score (“MOS”) which represents the viewer's subjective perception of the video stream. The method takes into account various factors such as frame rate, frame types and sizes, decoding algorithms, propagated error rates, and the effect of video content on viewer perception. The method can be used for both encrypted and unencrypted video streams.

The invention discloses a method for evaluating QoE (Quality of Experience) of mobile streaming media service perception experience by simulating user behaviors. The method comprises the following steps of: firstly, setting a mobile streaming media service QoE evaluation index system in which the user perception experience of mobile streaming media services are divided into parameters in three aspects of service access, service continuance and service completion; secondly, simulating the whole process of a user using the mobile streaming media services by a test terminal, and acquiring, respectively calculating key performance indexes (KPI) of the mobile streaming media services, calculating key quality indexes (KQI) of corresponding services of the mobile streaming media services, and performing comprehensive operation on the KQIs by means of a psychological model to obtain key experience indexes (KEI) of the corresponding services; and finally, comprehensively analyzing the KEI indexes to obtain a streaming media service QoE value which is in a five-grade marking system and equivalent to international standard MOS (Mean Opinion Score). The method disclosed by the invention is objective and practicable in evaluation parameter standard, simple in operation step, low in calculation complexity and easy to integrate, and is capable of obtaining relatively objective, just user experience perception quality by simulating the mobile streaming media service user.

An automated method for testing audio signal quality of cell phone transmissions provides a Mean Opinion Score (MOS) output using inexpensive test components. The test system uses a server computer to eliminate the need for expensive faders used in a bench test system. The server computer manipulates data packets from the reference media file to simulate impairments, including losses, errors, noise and jitter, at a much lower cost than using actual faders. Transmission through two separate radio access networks RANs is provided to simulate two parties communicating using separate mobile devices (an end-to-end test solution) with a single cell phone.

The invention provides a method for evaluating user quality of experience (QoE) of WAP (Wireless Application Protocol) services by simulating a user behavior. The method comprises the following steps of: at first, setting a set of a QoE evaluation index system consisting of experience property parameters of WAP services, which respectively comprise three applications of webpage browse, file upload and file download on own three aspects of service accessibility, service maintenance and service integrity; secondly, using a test terminal to simulate an entire process that a user uses the WAP services, and respectively collecting and calculating key performance indicators (KPI) of the WAP services, so as to calculate corresponding key quality indicators (KQI); and comprehensively calculating the KQIs by using a mental model to obtain corresponding key experience indicators (KEI) of the WAP services, and obtaining QoE values of the WAP service in a five-grade marking system, which are equivalent to an international standard mean opinion score (MOS). The method provided by the invention has the advantages of objective and practical selected evaluation parameter standards, simple operation steps, low computation complexity, and easiness of realization and integration, and can obtain relatively objective and just perceived quality of user experience by simulating the user behavior.

The invention relates to a device for estimating the quality of experience (QoE) for an internet protocol television (IPTV) user, comprising a network transmission detection module, a video coding detection module and a comprehensive analysis module, wherein the network transmission detection module is connected with the comprehensive analysis module by the video coding detection module and provided with a video streaming input end. The invention also provides a method for estimating the QoE for an IPTV user, which is realized based on the device. In the method, after the network transmission detection module acquires video streaming, the network transmission detection module detects the video streaming to acquire network transmission influence parameters; then the video coding detection module detects the video streaming to acquire video coding influence parameters; and finally the comprehensive analysis module calculates the sensory mean opinion score (MOS) of the user in accordance with the network transmission influence parameters and the video coding influence parameters so as to realize the estimation for subjective video quality. The device and method provided by the invention can be used to effectively improve the QoE of the existing IPTV.

Embodiments of the invention disclose a method and a device for determining the voice service quality of a user, which belong to the technical field of communication and are used for objective and accurate assessment of VOLTE voice service quality. The method comprises: voice over long term evolution (VOLTE) call detailed event record data of a user is obtained; according to the VOLTE call detailed event record data, target parameters of the user in a statistical period are calculated, including the sensed connected rate, the end-to-end time delay, the sensed dropped call rate, the voice mean opinion score (MOS), the abnormal ratio of the voice MOS and the number of poor voice quality events; the level of each parameter of the target parameters is determined, and the voice service quality of the user is determined according to the levels of the parameters. The method and the device can be used to determine the voice service quality of the user.

The invention discloses a method and a device for assessing quality of experience (QoE) of a TCP (Transmission Control Protocol) video stream service, and aims to monitor and record user interaction behaviors including pause, fast forward, backward and a selected resolution during watching of a video to be assessed on a client. The method comprises the following steps: acquiring a plurality of performance quantitative indexes representing the playing smoothness, content attraction degree and picture definition of the video to be assessed according to network layer performance, application layer performance and user interaction behaviors during watching of the video to be assessed on the client; inputting the performance quantitative indexes into a BP (Back Propagation) neural network model to obtain a subjective experience MOS (Mean Opinion Score) value; and determining the quality of experience (QoE) of the video to be assessed according to the MOS value. Through application of the scheme provided by the invention, an obtained assessment result can be closer to real experience of a user; the QoE assessment accuracy of the TCP video stream service is increased; and a good assessment effect is achieved.

The embodiment of the invention discloses a method and a device for evaluating the quality of a video, which relate to the technical field of communication and are invented for enhancing the accuracy of evaluating the quality of an Internet protocol television (IPTV) business. The method comprises the following steps of: obtaining a channel video stream and also obtaining the decoding characteristic parameter of a decoder, wherein the decoding characteristic parameter at least comprises decoding buffer capacity; and obtaining the loss rate of frame information according to the decoding characteristic parameter, also obtaining the MOS-V parameter of the mean opinion score of the video according to the channel video stream, and obtaining the MOS-V value of the channel video stream according to the loss rate of the frame information and the MOS-V parameter. The embodiment of the invention is mainly used in a technology for evaluating the quality of the video.

A method for calculating a mean opinion score (MOS) during an ongoing Voice over Internet Protocol (VoIP) call is provided. The method may include determining a time delay between a VoIP source and a VoIP destination connected by a communications network. A start recording message is sent from the VoIP source to the VoIP destination. A first recorded call sample from the VoIP source and a second recorded call sample from the VoIP destination are generated, whereby the first and the second recorded call sample are generated with a recording delay value corresponding the determined time delay for synchronizing the first and the second recorded call sample. Using an intrusive call quality measurement, a first MOS value is calculated based on the first and the second recorded call sample. Using a non-intrusive call quality measurement, a second MOS value is calculated based on the first MOS value.

Objective video quality assessment models at media-layer or at packet-layer are known for estimating audio/video quality of experience. Existing models are not able to provide stable performance. A method for enabling quality assessment of a stream of frames of video data comprises receiving a sequence of packets, generating a set of parameters and inserting said generated set of parameters as side information into said stream of frames, wherein at least one parameter refers to a video slice level. A method for assessing the quality of a stream of frames of video data comprises receiving a sequence of packets, extracting a set of parameters from said sequence of packets and generating an estimated mean opinion score, wherein the video data comprise a slice level and wherein the extracted set of parameters comprises at least one parameter that refers to a video slice level.

Disclosed herein are an apparatus and method for measuring quality of an image received via a communication network. The apparatus includes an interface unit, a codec unit, a test image detection unit, and a Mean Opinion Score (MOS) measurement unit. The interface unit receives an image, including a start synchronization image and a test image via a communication network. The codec unit decodes the received image into a color signal. The test image detection unit detects any one value of brightness, saturation and hue information of the color signal input from the codec unit, calculates an average value for each frame, and detects the test image from the received image based on the calculated average value. The MOS measurement unit synchronizes the test image with a corresponding reference image, compares the quality of the test image with the quality of the reference image, calculates an MOS value based on the results of the comparison, and outputs the MOS value.

The invention discloses a method and device for detecting the service quality of an IP (Internet Protocol) access network. The method comprises the steps as follows: network side call information of a call and media signals are collected on a network side; and the call quality parameter MOS (mean opinion score) of a tested call is acquired on the network side according to the call information and the media signals. Through application of the invention, the problem that in correlation techniques, the service quality of an IP access network can not be measured accurately due to distemperedness in evaluation of the service quality of the IP access network can be solved, further the service quality of the IP access network can be evaluated accurately, so that the system performance can be improved.

The invention provides a method and device for evaluating voice quality and belongs to the communication field. The method for evaluating voice quality comprises steps of: setting conversation parameters required by voice conversation, wherein the conversation parameter at least includes a maximum value of client jitter buffer memory and network jitter; acquiring degeneration voice samples corresponding to multiple groups of conversation parameters, computing a transmission damage coefficient R according to the acquired multiple degeneration voice samples and the conversation parameters; and obtaining a mean opinion score (MOS) of the voice quality according to the transmission damage coefficient R. The method and the device may accurately evaluate the voice quality based on an IP network.

The invention discloses an improved collaborative filtering recommendation method based on user characteristics. The method comprises the following steps that according to the mean opinion score of all users, an original user opinion score range is amended, according to the mean value of the modified user opinion score range and the mean opinion score of all users, original user opinion scores are amended, and after normalization processing, user opinion scores are obtained; according to the user opinion scores obtained after normalization processing, adjustment and normalization processing are conducted on the mean value of score difference values, through the combination with an original Jaccard similarity coefficient, the improved Jaccard similarity coefficient is obtained, and the similarity of the user opinion scores is obtained; according to the gender, age and job characteristic information of users, the similarity of user attributes is calculated; the similarity of the user opinion scores and the similarity of user attributes are combined to serve as the final user similarity, and nearest neighbor computing is conducted, and a recommendation list is generated. The method improves the recommendation quality of the traditional user-based collaborative filtering algorithm and reduces the influence of the data sparseness problem to a certain extent.

The embodiment of the invention relates to a mapping algorithm from PSNR (Peak Signal-to-Noise Ratio) to MOS (Mean Opinion Score) in a video system. The technical scheme is specific to received video frame sequences. The invention aims at providing the mapping algorithm for accurately mapping PSNR to MOS. The special implementation method is as follows: firstly extracting characteristic information from the received video frame sequences, wherein the characteristic information mainly comprises pixel and brightness information in the video frame sequences, then carrying out PSNR algorithm based on MSE (Mean Square Error), finally accurately mapping the PSNR to MOS by introducing an S type Sigmoid mapping function, and outputting a MOS value.

The embodiment of the invention relates to a mapping method from video objective parameters to QoE (Quality of Experience) based on video contents. The mapping method is specific to a wireless video transmission system. The invention aims at providing a QoE mapping scheme based on the video contents. The special implementation method is as follows: a corresponding MOS component to which each data packet corresponds is obtained by adopting a certain mapping method according to the contribution degree of each data packet contained in a video image frame to the whole visual effect of images. Simultaneously, the MOS (Mean Opinion Score) component obtained by adopting the technical scheme can be used as the basis of resource scheduling, and the purpose of high efficiency and energy saving in the wireless transmission process of videos is achieved.

A method for estimating mean opinion score or naturalness of synthesized speech is provided. The method includes using an objective measure that has components derived directly from textual information used to form synthesized utterances. The objective measure has a high correlation with mean opinion score such that a relationship can be formed between the objective measure and corresponding mean opinion score. An estimated mean opinion score can be obtained easily from the relationship when the objective measure is applied to utterances of a modified speech synthesizer.

In one embodiment, the quality of experience for a multi-part conference call is determined. Values for network characteristics for a conference call between at least three parties is captured using a multi-party conference call system. The network characteristics encompasses at least parameters expressed in an E-Model R-Factor equation. A quality of experience (QoE) is determined that accounts for degradation effects. The determined QoE is represented as a corrected mean opinion score (MOS) perceived by the receiving party. A controllable parameter of the conference call is dynamically and automatically modified to positively affect the determined QoE of the receiving party when the QoS is below a designated minimal QoE threshold.

The present invention provides an output-based objective voice quality evaluation method, comprising the following steps: calculating the Mel-frequency cepstrum coefficient of a distorted voice transmitted through a system; obtaining a reference model conforming to human auditory characteristics; performing consistency measurement and calculation on the Mel-frequency cepstrum coefficient of the distorted voice and the reference model conforming to human auditory characteristics; inserting a sequence in an original voice; calculating the bit error rate of the sequence extracted from distorted voice after the system transmission; according to the consistency measurement and the bit error rate, establishing the mapping relationship between the subjective MOS (mean opinion score) and the consistency measurement; obtaining an objective prediction model for the MOS of the voice to be evaluated; and objectively evaluating the voice quality through the objective prediction model. The method of the invention contains simple steps, is convenient to use, and can evaluate the voice quality objectively and effectively, without relying on the subjective evaluation.

The invention discloses a method for optimizing quality of service of a wireless streaming medium and a device. The method for optimizing the quality of the service of the wireless streaming medium is applied to a long term evolution (LTE) system and includes that network-side equipment receives a wireless streaming media playing request sent by a user terminal; the network-side equipment confirms a video source bit rate of the wireless streaming media requested to play according to the received wireless streaming media playing request and distributes band width for the user terminal according to the video source bit rate; and when the network-side equipment receives the value of mean opinion score (MOS) of the streaming media fed back by the user terminal, the network-side equipment adjusts the band width of the user terminal according to the value of the MOS of the streaming media. According to the method for optimizing the quality of service of the wireless streaming media and the device, the LTE band width distribution is reasonable, the LTE band width resource waste is reduced, and simultaneously the MOS of the wireless streaming media is guaranteed.