JP2005244321A - Method for estimating quality of audio video communication service and apparatus thereof - Google Patents

Method for estimating quality of audio video communication service and apparatus thereof Download PDF

Info

Publication number
JP2005244321A
JP2005244321A JP2004047866A JP2004047866A JP2005244321A JP 2005244321 A JP2005244321 A JP 2005244321A JP 2004047866 A JP2004047866 A JP 2004047866A JP 2004047866 A JP2004047866 A JP 2004047866A JP 2005244321 A JP2005244321 A JP 2005244321A
Authority
JP
Japan
Prior art keywords
video
audio
quality
evaluation value
quality evaluation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
JP2004047866A
Other languages
Japanese (ja)
Other versions
JP4027330B2 (en
Inventor
Takanori Hayashi
孝典 林
Kazuhisa Yamagishi
和久 山岸
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nippon Telegraph and Telephone Corp
Original Assignee
Nippon Telegraph and Telephone Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nippon Telegraph and Telephone Corp filed Critical Nippon Telegraph and Telephone Corp
Priority to JP2004047866A priority Critical patent/JP4027330B2/en
Publication of JP2005244321A publication Critical patent/JP2005244321A/en
Application granted granted Critical
Publication of JP4027330B2 publication Critical patent/JP4027330B2/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Landscapes

  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)

Abstract

<P>PROBLEM TO BE SOLVED: To provide a method for estimating quality of audio video communication services for obtaining an overall quality evaluation scale for a communication service using audio and video media. <P>SOLUTION: The method includes the steps of: receiving an audio quality evaluation value representing bodily sensation of audio by a communication party, a video quality evaluation value representing bodily sensation of video by the communication party, and a response quality evaluation value representing bodily sensation of a response delay of audio and video by the communication party; and summating a value resulting from weighting the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation value to a weighted product of two or three of the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation value and estimating the overall quality with respect to the audio video communication service on the basis of the summed value, and the method estimates the overall quality of the audio video communication service by evaluating the interaction of the audio quality and the video quality. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

本発明は、音声及び映像メディアを用いてネットワーク経由で通信相手と会話可能なシステムにおける音声・映像通信サービス品質推定方法及び装置に関するものである。   The present invention relates to an audio / video communication service quality estimation method and apparatus in a system capable of talking with a communication partner via a network using audio and video media.

インターネットのアクセス回線の高速・広帯域化に伴い、音声・映像メディアを用いた双方向リアルタイム通信サービス(例として、テレビ電話/会議サービス、コラボレーションサービス等)が期待されている。インターネットは必ずしも通信品質の保証されないネットワークであるため、音声及び映像メディアを用いて通信を行う場合、通信者(ユーザ)間のネットワークの回線帯域が狭かったり、回線が輻輳したりすると、音声や映像メディアに対してユーザが体感する品質(主観品質)が劣化してしまう。具体的には、音声に品質劣化が加わると、途切れ・雑音・応答の遅れ等として知覚され、映像に品質劣化が加わると、ぼけ・にじみ・モザイク状の歪・ぎくしゃく感・応答の遅れ等として知覚される。また、音声・映像メディア信号送信時の処理時間(音声・映像の符号化処理時間、送信バッファ時間等)、ネットワークにおける遅延時間(ネットワーク構成、通信者間の物理的距離等)、音声・映像メディア信号受信時の処理時間(受信バッファ時間、音声・映像の復号時間)に起因する遅延時間等によって、音声や映像の応答の遅れが知覚される場合がある。上記サービスを品質良く提供するためには、サービス提供に先立った品質設計やサービス開始後の品質管理が重要となり、このためには、ユーザが享受する品質を適切に表現でき、しかも簡便かつ効率的な品質評価技術の開発が必要となる。   As Internet access lines increase in speed and bandwidth, two-way real-time communication services using audio / video media (for example, videophone / conference services, collaboration services, etc.) are expected. Since the Internet is not necessarily a network with guaranteed communication quality, when communication is performed using audio and video media, if the line bandwidth of the network between communication parties (users) is narrow or the line is congested, audio and video The quality (subjective quality) experienced by the user with respect to the media deteriorates. Specifically, when quality degradation is added to audio, it is perceived as discontinuity, noise, response delay, etc., and when quality degradation is added to video, blur, blur, mosaic distortion, jerky feeling, response delay, etc. Perceived. Also, processing time when transmitting audio / video media signals (audio / video encoding processing time, transmission buffer time, etc.), network delay time (network configuration, physical distance between communicators, etc.), audio / video media There may be a case where a delay in response of audio or video is perceived due to a delay time or the like due to processing time (reception buffer time, audio / video decoding time) at the time of signal reception. In order to provide the above services with good quality, quality design prior to service provision and quality management after service start are important. For this purpose, the quality enjoyed by the user can be expressed appropriately, and it is simple and efficient. Development of new quality evaluation technology is required.

従来、音声品質を推定する技術については、例えば、国際標準化機関ITU−T(International Telecommunication Union Telecommunication Standardization Sector)勧告 P.862において音声品質客観評価尺度PESQ(Perceptual Evaluation of Speech Quality)が規定されている。また、映像品質を推定する技術についても、ITU−T勧告J.144等において映像品質客観評価尺度が記載されており、専門家機関であるVQEG(Video Quality Expert Group, URL:http://www.vqeg.org/)等においても継続して議論が行われている。これらの客観品質評価技術は、ある一定の条件下で主観品質の統計的曖昧さと同程度の推定誤差で主観品質を推定可能にしている。   Conventionally, with regard to a technique for estimating voice quality, for example, International Telecommunication Union Telecommunication Standardization Sector (ITU-T) Recommendation In 862, a speech quality objective evaluation scale PESQ (Perceptual Evaluation of Speech Quality) is defined. Also, regarding the technology for estimating the video quality, ITU-T Recommendation J.I. The video quality objective evaluation scale is described in 144 etc., and it is continuously discussed in VQEG (Video Quality Expert Group, URL: http://www.vqeg.org/) etc. Yes. These objective quality evaluation techniques make it possible to estimate the subjective quality with an estimation error comparable to the statistical ambiguity of the subjective quality under certain conditions.

従来の技術1の音声映像総合品質推定方法(特許文献1 参照)は、原音声に雑音を付加した雑音付加音声と原画像に雑音を付加した雑音付加映像により評価用標準信号を構成し、原音声への雑音付加量により決まる音声品質を表すパラメータQaと原画像への雑音付加量により決まる映像品質を表すパラメータQvにより、上記評価用標準信号の総合品質を変化させた場合に総合品質を一元的に表すパラメータQavを規定し、このQavをQaとQvにより推定する関係式を主観評価により導出する。
従来の技術2の通信・放送ネットワークを介した信号伝送の品質評価システム(特許文献2 参照)は、評価対象たる通信・放送ネットワークに対してテスト用の入力信号を入力し、入力信号は通信・放送ネットワーク内で劣化が生じ、その伝送結果が出力され、客観品質評価部に入力される。客観品質評価部では入力信号と出力信号とを比較して通信・放送ネットワーク内での品質の劣化を推定して、品質の評価を行う。
特開平8−289333号公報(要約、構成) 特開2001−298428(要約、構成)
In the conventional audio / video total quality estimation method (see Patent Document 1), a standard signal for evaluation is composed of a noise-added voice in which noise is added to the original voice and a noise-added video in which noise is added to the original image. The overall quality is unified when the overall quality of the standard signal for evaluation is changed by the parameter Qa representing the audio quality determined by the amount of noise added to the audio and the parameter Qv representing the video quality determined by the amount of noise added to the original image. A parameter Qav is expressed, and a relational expression for estimating this Qav by Qa and Qv is derived by subjective evaluation.
A conventional signal transmission quality evaluation system (see Patent Document 2) via a communication / broadcasting network inputs a test input signal to the communication / broadcasting network to be evaluated. Degradation occurs in the broadcasting network, and the transmission result is output and input to the objective quality evaluation unit. The objective quality evaluation unit compares the input signal and the output signal to estimate the deterioration of the quality in the communication / broadcasting network, and evaluates the quality.
Japanese Patent Laid-Open No. 8-289333 (Summary, Configuration) JP 2001-298428 (Abstract, Configuration)

しかしながら、上記の客観品質評価尺度は、音声メディアあるいは映像メディア等の個別メディアの品質を取り扱っているのがほとんどであり、音声及び映像メディアを用いた通信サービスの総合的な品質評価尺度として利用することができないという問題がある。また、テレビ電話/会議サービスやコラボレーションサービス等のような双方向通信サービスの場合には、各メディアの伝送遅延時間やメディア間の遅延時間のずれもサービスの品質を劣化させる原因となり得るが、上記と同様に品質評価尺度として考慮されていないという問題がある。   However, most of the above objective quality evaluation measures deal with the quality of individual media such as audio media and video media, and are used as a comprehensive quality evaluation measure for communication services using audio and video media. There is a problem that can not be. In addition, in the case of a two-way communication service such as a videophone / conference service or a collaboration service, the transmission delay time of each medium and the delay time between the media may cause the service quality to deteriorate. There is a problem that it is not considered as a quality evaluation scale.

従来の技術1においては、テレビ放送のような片方向の音声・映像サービスを前提としており、双方向性すなわち本発明における応答品質を考慮していない。また、従来の技術2においては、音声や映像信号の品質評価システムを実現しているが、ユーザが享受する音声や映像の品質をどのように取り扱って総合品質を導出するのかについては全く言及していない。
本発明は、上記に鑑みてなされたもので、その目的とするところは、音声・映像メディアを用いた双方向リアルタイム通信サービスの総合的な品質を求めることを可能とする音声・映像通信サービス品質推定方法及びその装置を提供することにある。
Prior art 1 is based on a one-way audio / video service such as television broadcasting, and does not consider bidirectionality, that is, response quality in the present invention. In the prior art 2, a quality evaluation system for audio and video signals is realized, but no mention is made of how to handle the quality of audio and video enjoyed by the user to derive the total quality. Not.
The present invention has been made in view of the above, and an object of the present invention is to provide an audio / video communication service quality capable of obtaining a comprehensive quality of a bidirectional real-time communication service using audio / video media. An estimation method and an apparatus thereof are provided.

上記の目的を達成するため、請求項1記載の本発明は、音声及び映像メディアを用いてネットワーク経由で通信相手と会話可能なシステムにおいて、音声に対して通信者が体感する音声品質評価値と、映像に対して通信者が体感する映像品質評価値と、音声及び映像の応答の遅れに対して通信者が体感する応答品質評価値を入力するステップと、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値を重み付けた値と、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値の2つあるいは3つの積を重み付けた値の加算から、音声・映像通信サービスに対する総合的な品質を推定するステップとを備えることを要旨とする。また、請求項2記載の本発明は、請求項1の発明に対して、音声に対して通信者が体感する音声品質評価値を推定するステップと、映像に対して通信者が体感する映像品質評価値を推定するステップと、音声及び映像の応答遅れに対して通信者が体感する応答品質評価値を推定するステップとを備えることを要旨とする。   In order to achieve the above object, the present invention according to claim 1 is an audio quality evaluation value that a communicator can experience with respect to audio in a system that can communicate with a communication partner via a network using audio and video media. Inputting a video quality evaluation value experienced by a communicator with respect to video, a response quality evaluation value experienced by a communicator with respect to a delay in response of audio and video, the audio quality evaluation value, and the video quality From the addition of an evaluation value, a value obtained by weighting the response quality evaluation value, and a value obtained by weighting two or three products of the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation value, audio / video communication And a step of estimating an overall quality for the service. According to a second aspect of the present invention, in contrast to the first aspect of the present invention, a step of estimating a voice quality evaluation value experienced by a communicator for voice and a video quality experienced by a communicator for video are provided. The gist is to include a step of estimating an evaluation value and a step of estimating a response quality evaluation value experienced by a communicator with respect to a response delay of audio and video.

請求項3記載の本発明は、音声および映像メディアを用いてネットワーク経由で通信相定と会話可能なシステムにおいて、音声に対して通信者が体感する音声品質評価値と、映像に対して通信者が体感する映像品質評価値と、音声及び映像の応答の遅れに対して通信者が体感する応答品質評価値を入力する手段と、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値を重み付けた値と、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値の2つあるいは3つの積を重み付けた値の加算から、音声・映像通信サービスに対する総合的な品質を推定する手段とを備えることを要旨とする。また、請求項4記載の本発明は、請求項3の発明に対して、音声に対して通信者が体感する音声品質評価値を推定する手段と、映像に対して通信者が体感する映像品質評価値を推定する手段と、音声及び映像の応答の遅れに対して通信者が体感する応答品質評価値を推定する手段とを備えることを要旨とする。   According to a third aspect of the present invention, there is provided a speech quality evaluation value that a communicator experiences with respect to voice and a communicator with respect to video in a system that can communicate and communicate with each other via a network using audio and video media. Means for inputting a video quality evaluation value experienced by the user and a response quality evaluation value experienced by a communicator with respect to a delay in response of audio and video, the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation From the sum of the weighted value and the weighted value of two or three products of the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation value, the overall quality for the audio / video communication service is obtained. And a means for estimating. Further, the present invention as set forth in claim 4, in contrast to the invention according to claim 3, means for estimating a voice quality evaluation value experienced by a communicator with respect to voice, and video quality experienced by a communicator with respect to video The gist of the present invention is to include means for estimating an evaluation value and means for estimating a response quality evaluation value experienced by a communicator with respect to delays in voice and video responses.

以上のような音声・映像通信サービス品質推定方法及びその装置では、音声品質、映像品質、応答品質の相互作用を評価して、音声・映像通信サービスの総合的な品質を推定することが可能となるため、ユーザに対してある一定以上の品質を保つための音声品質、映像品質、応答品質への要求条件を明確にすることができる。これにより、上記サービスで用いるアプリケーションパラメータ(例えば、符号化速度、映像フレームレート等の値)やネットワーク品質パラメータ(例えば、パケット損失率、遅延時間等の許容値)の設計、提供中のサービスの品質実態を把握・管理することが可能となる。   The audio / video communication service quality estimation method and apparatus as described above can estimate the overall quality of the audio / video communication service by evaluating the interaction of audio quality, video quality, and response quality. Therefore, it is possible to clarify the requirements for audio quality, video quality, and response quality for maintaining a certain level of quality for the user. As a result, application parameters (for example, values such as encoding speed and video frame rate) used in the service and network quality parameters (for example, allowable values such as packet loss rate and delay time) are designed and the quality of service being provided. It becomes possible to grasp and manage the actual situation.

本発明によれば、音声品質、映像品質、応答品質の相互作用を評価して、音声・映像通信サービスの総合的な品質を推定することが可能となるため、サービスを利用するユーザに対してある一定以上の品質を保っているかどうかを容易に判断することができる。また、品質をより改善するための指針として、音声品質、映像品質、応答品質の何を改善すればよいかを把握することもできる。これらにより、上記サービスで用いるアプリケーションパラメータ(例えば、符号化速度、映像フレームレート等の値)やネットワーク品質パラメータ(例えば、パケット損失率、遅延時間等の許容値)の設計や、提供中のサービスの品質実施を把握・管理することが可能となる。   According to the present invention, it is possible to estimate the overall quality of an audio / video communication service by evaluating the interaction of audio quality, video quality, and response quality. It is possible to easily determine whether or not a certain level of quality is maintained. Further, as a guideline for further improving the quality, it is possible to grasp what should be improved among the audio quality, the video quality, and the response quality. As a result, application parameters (for example, values such as encoding speed and video frame rate) used in the service and network quality parameters (for example, allowable values such as packet loss rate and delay time) can be designed and It becomes possible to grasp and manage quality implementation.

以下、図面を用いて本発明の実施形態を説明する。
(実施形態1)
図1は本発明の実施形態1に関わる音声・映像通信サービス品質推定システムの構成を示す図である。図1に示すように音声・映像通信サービス品質推定システム100は、音声品質推定部110、映像品質推定部120、応答品質推定部130、音声・映像通信サービス品質推定部140より構成されている。
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
(Embodiment 1)
FIG. 1 is a diagram showing the configuration of an audio / video communication service quality estimation system according to Embodiment 1 of the present invention. As shown in FIG. 1, the audio / video communication service quality estimation system 100 includes an audio quality estimation unit 110, a video quality estimation unit 120, a response quality estimation unit 130, and an audio / video communication service quality estimation unit 140.

次に、本発明の音声・映像通信サービス品質推定システムを介した総合品質の推定の流れを説明する。
音声品質推定部110は、送信音声(符号化・伝送装置への入力音声信号)及び受信音声(符号化・伝送・復号された出力音声信号)を入力とし、音声品質推定部110内の品質推定は、前述のITU−T勧告P.862等のアルゴリズムを適用することで実現することが可能となる。
映像品質推定部120は、送信映像(符号化・伝送装置への入力映像信号)及び受信映像(符号化・伝送・復号された出力映像信号)を入力とし、映像品質評価値を出力する。
映像品質推定部120内の品質推定は、前述のITU−T勧告J.144等のアルゴリズムを適用することで実現することが可能となる。ここで、音声品質あるいは映像品質を推定する際には、送受信信号の同期をとることが必要となるが、同期がとれた送受信信号は相関が高くなることを利用してずれた時間(符号化・伝送・復号の処理時間)すなわち遅延時間を求めることが可能である。
音声信号の遅延時間と映像信号の遅延時間を求めて応答品質推定部130への入力とし、応答品質評価値を出力する。
応答品質推定部130内の品質推定は、予め求めておいた遅延時間と応答品質の関係から導出する。その後、音声品質評価値、映像品質評価値、応答品質評価値を入力とした音声・映像通信サービス品質推定部140において、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値を重み付けた値と、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値の2つあるいは3つの積を重み付けた値の加算から、音声・映像通信サービスに対する総合的な品質を推定し、相互品質評価値を出力する。
Next, the overall quality estimation flow through the audio / video communication service quality estimation system of the present invention will be described.
Speech quality estimation section 110 receives transmission speech (input speech signal to the encoding / transmission apparatus) and reception speech (encoded speech transmission / decoded output speech signal), and performs quality estimation in speech quality estimation section 110. Is the above-mentioned ITU-T recommendation P.I. This can be realized by applying an algorithm such as 862.
The video quality estimation unit 120 receives the transmission video (input video signal to the encoding / transmission apparatus) and the reception video (encoded / transmitted / decoded output video signal) and outputs a video quality evaluation value.
The quality estimation in the video quality estimation unit 120 is performed according to the above-mentioned ITU-T recommendation J.I. It can be realized by applying an algorithm such as 144. Here, when estimating the audio quality or the video quality, it is necessary to synchronize the transmission / reception signals. However, the synchronized transmission / reception signals are shifted by using the fact that the correlation is high (encoding). (Transmission / decoding processing time), that is, a delay time can be obtained.
The delay time of the audio signal and the delay time of the video signal are obtained and input to the response quality estimation unit 130, and a response quality evaluation value is output.
The quality estimation in the response quality estimation unit 130 is derived from the relationship between the delay time obtained in advance and the response quality. Thereafter, in the audio / video communication service quality estimation unit 140 having the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation value as inputs, the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation value are weighted. A total quality for the voice / video communication service is estimated by adding a value obtained by weighting two or three products of the audio quality evaluation value, the video quality evaluation value, and the response quality evaluation value, Output mutual quality evaluation value.

上記の流れの具体例として、実際にユーザの主観品質評価実験によって遅延時間と応答品質の関係を求めた結果を図2に示す。図2は、1対1のテレビ電話サービスにおいて1分間自由に会話した場合の片道遅延時間と5段階品質尺度により求めた平均オピニオン評点MOS(Mean opinion Score:「非常に良い」、「良い」、「普通」、「悪い」、「非常に悪い」の5段階の評価尺度に対してそれぞれ5〜1点を付け、評価者が投票した得点の平均値を平均オピニオン評点と呼ぶ)の関係を示している。図2では、応答品質のMOS値であることがわかるようにdを添字として付している。また、音声信号と映像信号は同じ時間だけ遅れている(同期している)場合に結果である。ここで、評価者はインターネットを利用する20〜39歳までの男女計32名である。図2より、片道遅延時間と応答品質の関係を定式化して対応関係を求めておくことは容易である。   As a specific example of the above flow, FIG. 2 shows the result of actually obtaining the relationship between the delay time and the response quality by the user's subjective quality evaluation experiment. FIG. 2 shows an average opinion score MOS (Mean opinion score: “very good”, “good”) obtained from a one-way delay time in a one-on-one videophone service and a one-way delay time and a five-level quality scale. 5 to 1 for each of the “normal”, “bad”, and “very bad” evaluation scales, and the average value of the votes voted by the evaluator is called the average opinion score) ing. In FIG. 2, d is attached as a subscript so that it can be understood that the response quality is a MOS value. The result is when the audio signal and the video signal are delayed (synchronized) by the same time. Here, the evaluators are a total of 32 men and women from the age of 20 to 39 who use the Internet. From FIG. 2, it is easy to formulate the relationship between the one-way delay time and the response quality and obtain the correspondence.

次に、音声・映像通信サービスに対する総合的な品質の推定方法の具体例を示す。
上記と同じ主観品質評価実験により、音声品質評価値MOSa、映像品質評価値MOSv、応答品質評価値MOSdと総合品質MOStの関係を定式化した結果、MOSt=α・MOSa+β・MOSv+γ・MOSd+δ・MOSa・MOSv+ε・MOSa・MOSd+ψ・MOSv・MOSd+φ・MOSa・MOSv・MOSd+μという関数で推定可能であることがわかった。ここで、α、β、γ、δ、ε、ψ、φ、μは定数で、音声・映像通信サービス(ここではテレビ電話サービス)をどのようなシーンで利用するのか、どのような会話を行うか等により変化する値である。想定するサービス利用シーンを決定し、一度主観品質評価実験を行うことでこれらの定数は求めることが可能である。
Next, a specific example of a comprehensive quality estimation method for an audio / video communication service will be described.
In the same subjective quality evaluation experiment as described above, the relationship between the audio quality evaluation value MOSa, the video quality evaluation value MOSv, the response quality evaluation value MOSd, and the overall quality MOSt is formulated. It was found that this can be estimated by the function of MOSv + ε · MOSa · MOSd + ψ · MOSv · MOSd + φ · MOSa · MOSv · MOSd + μ. Here, α, β, γ, δ, ε, ψ, φ, and μ are constants, and in what scene the audio / video communication service (here, the videophone service) is used and what kind of conversation is performed. It is a value that changes depending on the above. These constants can be obtained by determining an assumed service usage scene and conducting a subjective quality evaluation experiment once.

各定数を求める方法について説明する。
まず、音声品質、映像品質、応答品質が異なる複数の実験条件を設定し、これらに対してITU−T勧告P.911に準拠した主観評価実験を行う。各品質は、音声・映像通信サービスの通信環境(パケット損失率、パケット遅延時間/ゆらぎ時間等のネットワーク品質パラメータ)が制御できる実験系(例えば、ネットワークエミュレータ装置を介して、音声・映像コミュニケーションサービスで用いる端末/アプリケーションを接続する)を用いることで制御可能である。主観評価実験では、被験者に想定するサービス利用シーンを模擬する会話を実施してもらい、音声品質、映像品質、応答品質の他に、音声・映像通信サービスに対する総合的な品質を評価し、前述のMOSa,MOSv,MOSd,MOStの値を求める。これらのデータから、MOStを目的変数、MOSa,MOSv,MOSdを説明変数とし、それぞれの交互作用を考慮した関数、MOSt=α・MOSa+β・MOSv+γ・MOSd+δ・MOSa・MOSv+ε・MOSa・MOSd+ψ・MOSv・MOSd+φ・MOSa・MOSv・MOSd+μにより重回帰分析を行うことにより、定数α、β、γ、δ、ε、ψ、φ、μの値を求めることができる。
A method for obtaining each constant will be described.
First, a plurality of experimental conditions having different audio quality, video quality, and response quality are set. Subjective evaluation experiment based on 911 is conducted. Each quality can be controlled by an audio / video communication service via an experimental system (for example, a network emulator device) that can control the communication environment of the audio / video communication service (network quality parameters such as packet loss rate, packet delay time / fluctuation time). Can be controlled by using a terminal / application to be used. In the subjective evaluation experiment, subjects were asked to conduct a conversation that simulates the service usage scene assumed, and in addition to voice quality, video quality, response quality, overall quality for voice / video communication services was evaluated. The values of MOSa, MOSv, MOSd, and MOSt are obtained. From these data, MOSt is an objective variable, MOSa, MOSv, and MOSd are explanatory variables, and a function that considers each interaction, MOSt = α · MOSa + β · MOSv + γ · MOSd + δ · MOSa · MOSv + ε · MOSa · MOSd + ψ · MOSv · MOSd + φ The values of the constants α, β, γ, δ, ε, ψ, φ, μ can be obtained by performing multiple regression analysis with MOSa, MOSv, MOSd + μ.

上記と同様に、自由に会話をする場合を想定した評価結果に本推定関数を適用した結果を図3に示す。横軸は実測により求めた総合品質MOSt、縦軸はMOSa,MOSv,MOSdの関数である上記推定式より求めた総合品質MOSt estを示している。殆どのデータが45度の線上に位置することから、上記推定式は非常に精度良く総合品質を推定していることがわかる。
以上の実施形態により、本発明が対象として課題を解決し、送受信した音声信号と映像信号から、音声・映像メディアを用いた双方向リアルタイム通信サービスの総合的な品質を求めることが可能となる。
Similarly to the above, FIG. 3 shows the result of applying this estimation function to the evaluation result assuming the case of having a free conversation. The horizontal axis represents the total quality MOSt obtained by actual measurement, and the vertical axis represents the total quality MOSt obtained from the above estimation formula that is a function of MOSa, MOSv, and MOSd. Indicates est. Since most of the data is located on the 45 degree line, it can be seen that the above estimation equation estimates the overall quality with very high accuracy.
According to the above embodiment, the present invention solves the problem, and it is possible to obtain the overall quality of the bidirectional real-time communication service using audio / video media from the transmitted and received audio signals and video signals.

(実施形態2)
実施形態1において、音声品質、映像品質、応答品質のそれぞれを推定するステップ/手段を備えていない実施形態、すなわち音声品質推定部110、映像品質推定部120、応答品質推定部130を除いた形態も本発明の範囲に含まれる。
(Embodiment 2)
Embodiment 1 which does not include steps / means for estimating each of audio quality, video quality, and response quality in Embodiment 1, that is, an embodiment excluding audio quality estimation unit 110, video quality estimation unit 120, and response quality estimation unit 130 Are also included within the scope of the present invention.

(実施形態3)
図4は、本発明の実施形態3に関わる音声・映像通信サービス品質推定システム構成を示す図である。
実施形態1で示した図1と同様に、図4の音声・映像通信サービス品質推定システム200は、音声品質推定部210、映像品質推定部220、応答品質推定部230、音声・映像通信サービス品質推定部240より構成されている。実施形態1とは、音声品質推定部210、映像品質推定部220、応答品質推定部230への入力信号が異なる。音声品質推定部210、映像品質推定部220では、送信音声あるいは送信映像がない場合の品質推定アルゴリズムを用いることで音声品質あるいは映像品質を推定することが可能となる。ただし、受信音声あるいは受信映像のみから音声と映像の遅延時間を求めることはできないため、別方法で遅延時間を求めて応答品質推定部230の入力とする必要がある。ネットワークの遅延時間を推定する方法については数多くの提案がされているため、ここでは省略する。図4の実施の形態では、音声と映像の両者を受信信号のみを入力としたが、音声あるいは映像のどちらか一方を受信信号のみとする実施形態についても本発明の範囲に含まれる。
(Embodiment 3)
FIG. 4 is a diagram showing the configuration of an audio / video communication service quality estimation system according to Embodiment 3 of the present invention.
Similar to FIG. 1 described in the first embodiment, the audio / video communication service quality estimation system 200 of FIG. 4 includes an audio quality estimation unit 210, a video quality estimation unit 220, a response quality estimation unit 230, an audio / video communication service quality. The estimation unit 240 is configured. The input signals to the audio quality estimation unit 210, the video quality estimation unit 220, and the response quality estimation unit 230 are different from those in the first embodiment. The audio quality estimation unit 210 and the video quality estimation unit 220 can estimate the audio quality or the video quality by using a quality estimation algorithm when there is no transmission audio or transmission video. However, since it is impossible to obtain the delay time between the audio and the video from the received audio or the received video alone, it is necessary to obtain the delay time by another method and input it to the response quality estimation unit 230. Since many proposals have been made for methods for estimating the delay time of the network, they are omitted here. In the embodiment of FIG. 4, only the received signal is input for both audio and video, but an embodiment in which either the audio or video is only the received signal is also included in the scope of the present invention.

本発明の音声・映像通信サービス品質推定システム(実施形態1)の構成を示す図。The figure which shows the structure of the audio | voice and video communication service quality estimation system (Embodiment 1) of this invention. 片道遅延時間と主観品質の関係を示す図。The figure which shows the relationship between one-way delay time and subjective quality. 本発明の実施形態1で用いた音声・映像通信サービス品質推定方法の評価精度を示す図。The figure which shows the evaluation precision of the audio | voice and video communication service quality estimation method used in Embodiment 1 of this invention. 本発明の音声・映像通信サービス品質推定システム(実施形態3)の構成を示す図。The figure which shows the structure of the audio | voice and video communication service quality estimation system (Embodiment 3) of this invention.

符号の説明Explanation of symbols

100,200・・・音声・映像通信サービス品質推定システム
110,210・・・音声品質推定部
120,220・・・映像品質推定部
130,230・・・応答品質推定部
140,240・・・音声・映像通信サービス推定部
100, 200 ... Voice / video communication service quality estimation system 110, 210 ... Audio quality estimation unit 120, 220 ... Video quality estimation unit 130, 230 ... Response quality estimation unit 140, 240 ... Audio / Video Communication Service Estimator

Claims (4)

音声及び映像メディアを用いてネットワーク経由で通信相手と会話可能なシステムにおける音声・映像通信サービス品質推定方法において、
音声に対して通信者が体感する音声品質評価値と、映像に対して通信者が体感する映像品質評価値と、音声及び映像の応答の遅れに対して通信者が体感する応答品質評価値を入力するステップと、
前記音声品質評価値、前記映像品質評価値、前記応答品質評価値を重み付けた値と、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値の2つあるいは3つの積を重み付けた値を加算し、加算した値から、音声・映像通信サービスに対する総合的な品質を推定するステップと、
を備えることを特徴とする音声・映像通信サービス品質推定方法。
In the audio / video communication service quality estimation method in a system capable of talking with a communication partner via a network using audio and video media,
The voice quality evaluation value experienced by the communicator with respect to the audio, the video quality evaluation value experienced by the communicator with respect to the video, and the response quality evaluation value experienced by the communicator with respect to the delay in the response of the audio and video. Step to enter,
Weighted two or three products of the audio quality evaluation value, the video quality evaluation value and the response quality evaluation value and the audio quality evaluation value, the video quality evaluation value and the response quality evaluation value Adding the values, and estimating the overall quality for the audio / video communication service from the added values;
An audio / video communication service quality estimation method comprising:
請求項1に記載の音声・映像通信サービス品質推定方法において、
音声に対して通信者が体感する音声品質評価値を推定するステップと、
映像に対して通信者が体感する映像品質評価値を推定するステップと、
音声及び映像の応答遅れに対して通信者が体感する応答品質評価値を推定するステップと、
を備えることを特徴とする音声・映像通信サービス品質推定方法。
The audio / video communication service quality estimation method according to claim 1,
Estimating a voice quality evaluation value experienced by a communication person with respect to the voice;
Estimating a video quality evaluation value experienced by a communication person for the video;
Estimating a response quality evaluation value experienced by a communication person with respect to a response delay of audio and video;
An audio / video communication service quality estimation method comprising:
音声及び映像メディアを用いてネットワーク経由で通信相手と会話可能なシステムにおける音声・映像通信サービス品質推定装置において、
音声に対して通信者が体感する音声品質評価値と、映像に対して通信者が体感する映像品質評価値と、音声及び映像の応答の遅れに対して通信者が体感する応答品質評価値を入力する手段と、
前記音声品質評価値、前記映像品質評価値、前記応答品質評価値を重み付けた値と、前記音声品質評価値、前記映像品質評価値、前記応答品質評価値の2つあるいは3つの積を重み付けた値を加算し、加算した値から、音声・映像通信サービスに対する総合的な品質を推定する手段と、
を備えることを特徴とする音声・映像通信サービス品質推定装置。
In an audio / video communication service quality estimation apparatus in a system capable of talking with a communication partner via a network using audio and video media,
The voice quality evaluation value experienced by the communicator with respect to the audio, the video quality evaluation value experienced by the communicator with respect to the video, and the response quality evaluation value experienced by the communicator with respect to the delay in the response of the audio and video. Means to input;
Weighted two or three products of the audio quality evaluation value, the video quality evaluation value and the response quality evaluation value and the audio quality evaluation value, the video quality evaluation value and the response quality evaluation value Means for adding the values, and estimating the total quality for the audio / video communication service from the added values;
An audio / video communication service quality estimation apparatus comprising:
請求項3に記載の音声・映像通信サービス品質推定装置において、
音声に対して通信者が体感する音声品質評価値を推定する手段と、
映像に対して通信者が体感する映像品質評価値を推定する手段と、
音声及び映像の応答の遅れに対して通信者が体感する応答品質評価値を推定する手段と、
を備えることを特徴とする音声・映像通信サービス品質推定装置。
In the audio / video communication service quality estimation apparatus according to claim 3,
Means for estimating a voice quality evaluation value experienced by a communication person with respect to the voice;
Means for estimating a video quality evaluation value experienced by a communication person for the video;
Means for estimating a response quality evaluation value experienced by a communicator with respect to delays in voice and video responses;
An audio / video communication service quality estimation apparatus comprising:
JP2004047866A 2004-02-24 2004-02-24 Voice / video communication service quality estimation method and apparatus Expired - Lifetime JP4027330B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2004047866A JP4027330B2 (en) 2004-02-24 2004-02-24 Voice / video communication service quality estimation method and apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2004047866A JP4027330B2 (en) 2004-02-24 2004-02-24 Voice / video communication service quality estimation method and apparatus

Publications (2)

Publication Number Publication Date
JP2005244321A true JP2005244321A (en) 2005-09-08
JP4027330B2 JP4027330B2 (en) 2007-12-26

Family

ID=35025632

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2004047866A Expired - Lifetime JP4027330B2 (en) 2004-02-24 2004-02-24 Voice / video communication service quality estimation method and apparatus

Country Status (1)

Country Link
JP (1) JP4027330B2 (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007029731A1 (en) * 2005-09-06 2007-03-15 Nippon Telegraph And Telephone Corporation Video communication quality estimation device, method, and program
JP2008219139A (en) * 2007-02-28 2008-09-18 Kddi Corp Server and method for testing call quality, communication terminal, and program
JP2009027432A (en) * 2007-07-19 2009-02-05 Nippon Telegr & Teleph Corp <Ntt> Video quality objective evaluation method, video quality objective evaluation device and program
EP2106153A1 (en) * 2008-03-28 2009-09-30 Deutsche Telekom AG Audio-visual quality estimation
JP2015012361A (en) * 2013-06-27 2015-01-19 日本電信電話株式会社 Qoe estimating device, qoe estimating method, and program
CN111507873A (en) * 2020-04-14 2020-08-07 四川聚阳科技集团有限公司 Classroom participation degree evaluation method based on sound and image joint sampling
CN113727100A (en) * 2021-09-30 2021-11-30 北京达佳互联信息技术有限公司 Method and device for diagnosing audio and video communication quality

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007029731A1 (en) * 2005-09-06 2007-03-15 Nippon Telegraph And Telephone Corporation Video communication quality estimation device, method, and program
KR100947275B1 (en) 2005-09-06 2010-03-11 니폰덴신뎅와 가부시키가이샤 Video communication quality estimation apparatus, method, and program
US8405773B2 (en) 2005-09-06 2013-03-26 Nippon Telegraph And Telephone Corporation Video communication quality estimation apparatus, method, and program
JP2008219139A (en) * 2007-02-28 2008-09-18 Kddi Corp Server and method for testing call quality, communication terminal, and program
JP4718501B2 (en) * 2007-02-28 2011-07-06 Kddi株式会社 Call quality test server and call quality test method
JP2009027432A (en) * 2007-07-19 2009-02-05 Nippon Telegr & Teleph Corp <Ntt> Video quality objective evaluation method, video quality objective evaluation device and program
EP2106153A1 (en) * 2008-03-28 2009-09-30 Deutsche Telekom AG Audio-visual quality estimation
EP2106154A1 (en) * 2008-03-28 2009-09-30 Deutsche Telekom AG Audio-visual quality estimation
US8531531B2 (en) 2008-03-28 2013-09-10 Deutsche Telekom Ag Audio-visual quality estimation
JP2015012361A (en) * 2013-06-27 2015-01-19 日本電信電話株式会社 Qoe estimating device, qoe estimating method, and program
CN111507873A (en) * 2020-04-14 2020-08-07 四川聚阳科技集团有限公司 Classroom participation degree evaluation method based on sound and image joint sampling
CN113727100A (en) * 2021-09-30 2021-11-30 北京达佳互联信息技术有限公司 Method and device for diagnosing audio and video communication quality

Also Published As

Publication number Publication date
JP4027330B2 (en) 2007-12-26

Similar Documents

Publication Publication Date Title
US8405773B2 (en) Video communication quality estimation apparatus, method, and program
Robitza et al. A modular http adaptive streaming qoe model—candidate for itu-t p. 1203 (“p. nats”)
Yamagishi et al. Qrp08-1: Opinion model for estimating video quality of videophone services
Yang et al. Content-adaptive packet-layer model for quality assessment of networked video services
CN109714557A (en) Method for evaluating quality, device, electronic equipment and the storage medium of video calling
JP4317540B2 (en) Video quality estimation apparatus, method and program
da Silva et al. Quality assessment of interactive voice applications
Usman et al. A no reference video quality metric based on jerkiness estimation focusing on multiple frame freezing in video streaming
Goudarzi et al. Audiovisual quality estimation for video calls in wireless applications
JP4490374B2 (en) Video quality evaluation apparatus and method
JP4510583B2 (en) Bidirectional multimodal service quality estimation apparatus and method
JP4027330B2 (en) Voice / video communication service quality estimation method and apparatus
JP4745721B2 (en) Network communication service satisfaction estimation device, method, and program
Wuttidittachotti et al. VoIP-quality of experience modeling: E-model and simplified E-model enhancement using bias factor
JP4460523B2 (en) User experience quality estimation apparatus, method, and program
JP4365291B2 (en) Quality estimation method and quality estimation apparatus in two-way communication service system
Yamagishi et al. Opinion model using psychological factors for interactive multimodal services
Vaalgamaa et al. Audiovisual communication
Han et al. Hybrid real-time quality assessment model for voice over IP
JP5952252B2 (en) Call quality estimation method, call quality estimation device, and program
JP2004222257A (en) Total call quality estimating method and apparatus, program for executing method, and recording medium thereof
Martínez-Rach et al. On the performance of video quality assessment metrics under different compression and packet loss scenarios
Su et al. Packet-layer quality assessment for networked video
Casas et al. End-2-end evaluation of ip multimedia services, a user perceived quality of service approach
Yamagishi et al. Verification of video quality opinion model for videophone services

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20050531

RD03 Notification of appointment of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7423

Effective date: 20050531

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20070928

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20071002

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20071009

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20101019

Year of fee payment: 3

R150 Certificate of patent or registration of utility model

Ref document number: 4027330

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20101019

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20111019

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20111019

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20121019

Year of fee payment: 5

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20121019

Year of fee payment: 5

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20131019

Year of fee payment: 6

S531 Written request for registration of change of domicile

Free format text: JAPANESE INTERMEDIATE CODE: R313531

R350 Written notification of registration of transfer

Free format text: JAPANESE INTERMEDIATE CODE: R350

EXPY Cancellation because of completion of term