Multi-language identification and transcription in Video Indexer

Multi-language speech transcription was recently introduced into Microsoft Video Indexer at the International Broadcasters Conference (IBC). It is available as a preview capability and customers can already start experiencing it in our portal. More details on all our IBC2019 enhancements can be found here.

Multi-language videos are common media assets in the globalization context, global political summits, economic forums, and sport press conferences are examples of venues where speakers use their native language to convey their own statements. Those videos pose a unique challenge for companies that need to provide automatic transcription for video archives of large volumes. Automatic transcription technologies expect users to explicitly determine the video language in advance to convert speech to text. This manual step becomes a scalability obstacle when transcribing multi-language content as one would have to manually tag audio segments with the appropriate language.

Microsoft Video Indexer provides a unique capability of automatic spoken language identification for multi-language content. This solution allows users to easily transcribe multi-language content without going through tedious manual preparation steps before triggering it. By that, it can save anyone with large archive of videos both time and money, and enable discoverability and accessibility scenarios.

Multi-language audio transcription in Video Indexer

The multi-language transcription capability is available as part of the Video Indexer portal. Currently, it supports four languages including English, French, German and Spanish, while expecting up to three different languages in an input media asset. While uploading a new media asset you can select the “Auto-detect multi-language” option as shown below.

Our application programming interface (API) supports this capability as well by enabling users to specify 'multi' as the language in the upload API. Once the indexing process is completed, the index JavaScript object notation (JSON) will include the underlying languages. Refer to our documentation for more details.

Additionally, each instance in the transcription section will include the language in which it was transcribed.

Customers can view the transcript and identified languages by time, jump to the specific places in the video for each language, and even see the multi-language transcription as video captions. The result transcription is also available as closed caption files (VTT, TTML, SRT, TXT, and CSV).

Methodology

Language identification from an audio signal is a complex task. Acoustic environment, speaker gender, and speaker age are among a variety of factors that affect this process. We represent audio signal using a visual representation, such as spectrograms, assuming that, different languages induce unique visual patterns which can be learned using deep neural networks.

Our solution has two main stages to determine the languages used in multi-language media content. First, it employs a deep neural network to classify audio segments with very high granularity, in other words, very few seconds. While a good model will successfully identify the underlying language, it can still miss-identify some segments due to similarities between languages. Therefore, we apply a second stage for examining these misses and smooth the results accordingly.

Next steps

We introduced a differentiated capability for multi-language speech transcription. With this unique capability in Video Indexer, you can become more effective about the content of your videos as it allows you to immediately start searching across videos for different language segments. During the coming few months, we will be improving this capability by adding support for more languages and improving the model’s accuracy.

For more information, visit Video Indexer’s portal or the Video Indexer developer portal, and try this new capability. Read more about the new multi-language option and how to use it in our documentation.

Please use our UserVoice to share feedback and help us prioritize features or email visupport@microsoft.com with any questions.
Quelle: Azure

Understanding Google Cloud Armor’s new WAF capabilities

Protecting applications exposed to the internet is an increasingly difficult job. Since we launched Google Cloud Armor last December, it has helped enterprises protect themselves and their users with a native solution that protects big and small applications from Distributed Denial of Service (DDoS) and targeted web attacks with custom security policies enforced at the edge of Google’s network, at Google-scale.Last week, we announced new web-application firewall (WAF) capabilities, now available in beta. With this release, Google Cloud Armor is expanding the scope of protection it provides for securing your applications and other workloads from DDoS and targeted web-based attacks. It can also help you meet compliance requirements from internal security policies as well as external regulatory requirements. Specifically, Google Cloud Armor now lets you create security policies or expand existing ones to enforce:Geo-based access controlsPre-configured WAF rules, and Custom L7 filtering policies using custom rulesVisibility into the usage and effectiveness of security controls as well as the protected applications is essential to security operations. Google Cloud Armor now sends findings to Cloud Security Command Center (Cloud SCC) to alert defenders of potential Layer 7 attacks. This is in addition to the rich set of telemetry that it already sends to Stackdriver Logging and Stackdriver Monitoring.Google Cloud Armor overviewGoogle Cloud Armor mitigates DDoS attacks and protects applications from the web’s most common attacks while allowing you to create custom L7 filtering policies to enforce granular access controls on public-facing applications and websites. Google Cloud Armor is deployed at the edge of Google’s network and tightly coupled with our global load balancing infrastructure. As a result, Google Cloud Armor helps you solve your most pressing application security and compliance needs at any scale, blocking unwelcome or malicious traffic at the edge of the network, far upstream of your VPCs or other infrastructure.What’s newThe following capabilities are now available in beta.Custom rules To ensure the safe operation and availability of protected applications, security controls need to be context-sensitive and tailored to the unique needs of individual applications. With Cloud Armor custom rules, you can now create rules with advanced match conditions to filter incoming traffic across a variety of attributes and parameters from Layers 3 through 7. To get started, you can find the full language specification and sample expressions in the security policy rules language reference.Custom rules can be as simple or complex as dictated by the security and business needs of your applications. Take, for example:This is an example rule that blocks incoming traffic that matches each of the conditions:From the United States, with a user agent that contains the phrase “Bad Bot,” and contains a cookie named “discount” with a value of “ab1d8732”Geo-based access controlsThere are times when you may need to limit access to an application to certain countries—whether it is for regulatory compliance, copyright licensing, or another business need. With Google Cloud Armor, you can now configure security policies to create allow lists or deny lists based on the country code of the client request attempting to reach your application. This ensures that you will only receive traffic from and serve content to users in specific countries. You can also use source geography in combination with other attributes in Cloud Armor’s custom rules language to apply fine-grained control over what can be accessed, by whom, and from where.Pre-configured WAF rules (SQLi & XSS)Google Cloud Armor now includes pre-configured WAF rules to protect applications from the web’s most common attack (e.g. OWASP Top 10 Risks), making it easier for you to configure and operate a web application firewall and meet your compliance and security needs. Today, Cloud Armor WAF rules protect you from the web’s most common attack types—SQL Injection and Cross-Site Scripting—with more pre-configured WAF rules on the way. We built these pre-configured WAF rules by implementing the signatures and sub-signatures described in the open source ModSecurity Core Rule Set for SQLi and XSS. In the WAF rule tuning guide, we also describe how to finetune the preconfigured rules to optimize on sensitivity levels and customize them on a per protected-application basis. Over time, we’ll introduce additional rules from the ModSecurity CRS to make it easier to protect your application from the OWASP Top 10 risks and beyond.Surfacing findings in the Cloud Security Command CenterGoogle Cloud Armor now automatically sends findings to Cloud SCC to alert you to suspicious Layer 7 traffic patterns. Organizations with Cloud SCC enabled will now receive real-time notifications of two events:Allowed Traffic Spike: A sudden increase in the volume of Layer 7 requests being allowed through an existing Google Cloud Armor security policy on a per backend service basis.Increasing Deny Ratio: A sudden increase in the ratio of traffic that is being denied compared to the total traffic targeting a particular backend service.Together these findings can alert application owners and incident responders of potential Layer 7 attacks while they are still ramping up. With early notice, incident responders can begin to investigate and triage earlier, deploying mitigating controls sooner to protect against an attack before it impacts the availability of your application. Next stepsWith the beta release of this rich set of WAF capabilities, Google Cloud Armor now enables enterprises of any size to easily protect your public facing applications while satisfying your risk and compliance needs. In addition, the new Google Cloud Armor telemetry in Cloud SCC helps to accelerate incidence detection and response to ensure the security and availability of mission-critical applications. Finally, the combination of Google Cloud Armor with Google Cloud Load Balancing lets you deploy to and customize Google’s global edge infrastructure to protect your applications against the web’s most common attacks, provide granular Layer 7 access controls, and defend against volumetric, protocol and application-level DDoS attacks.Google Cloud Armor WAF capabilities are publically available. To get started, navigate to Network Security -> Cloud Armor in the Google Cloud Console. Learn more: Google Cloud Armor product pageGoogle Cloud Armor documentationCustom Rules Language referenceWAF Rule Tuning Guide
Quelle: Google Cloud Platform

Star Citizen: Mit der Carrack ins neue Sonnensystem

Für Fans hätte die Citizencon 2949 in Manchester kaum besser laufen können: Bald können sie die Anvil Carrack fliegen. Der Saal tobte allerdings nicht für das Schiff am lautesten, denn Star Citizen wagt den Sprung in das erste neue Sonnensystem nach Stanton: Pyro. Von Oliver Nickel (Star Citizen, Games)
Quelle: Golem