We present MeetDot, a videoconferencing system with live translation captions overlaid on screen. The system aims to facilitate conversation between people who speak different languages, thereby reducing communication barriers between multilingual participants. Currently, our system supports speech and captions in 4 languages and combines automatic speech recognition (ASR) and machine translation (MT) in a cascade. We use the retranslation strategy to translate the streamed speech, resulting in caption flicker. Additionally, our system has very strict latency requirements to have acceptable call quality. We implement several features to enhance user experience and reduce their cognitive load, such as smooth scrolling captions and reducing caption flicker. The modular architecture allows us to integrate different ASR and MT services in our backend. Our system provides an integrated evaluation suite to optimize key intrinsic evaluation metrics such as accuracy, latency and erasure. Finally, we present an innovative cross-lingual word-guessing game as an extrinsic evaluation metric to measure end-toend system performance. We plan to make our system open-source for research purposes.

We describe the DiDi Labs system submitted for the IWSLT 2020 Offline Speech Translation Task (Ansari et al., 2020). We trained an end-to-end system that translates audio from English TED talks to German text, without producing intermediate English text. Our base system used the S-Transformer architecture (Di Gangi et al., 2019b), trained using the MuST-C dataset (Di Gangi et al., 2019a). We extended the system via decoder pre-training, pre-trained speech features, and text translation, but these extensions did not yield improved results.

Security Analysis of Multicast/Unicast Router Key Management Protocols Yiqi Huang Key Management Protocols (KMPs) are intended to manage cryptographic keys in a cryptosystem. KMPs have been standardized for Internet Protocol Security (IPsec), and these KMPs have been formally validated for their security properties. In the Internet, routing protocols have different requirements on their KMPs, which are not met by the existing IPsec KMPs, such as IKE, IKEv2, and GDOI. Protocol modeling has been used to analyze the security of the IPsec KMPs. For routing protocols, there are new KMPs proposed by the Keying and Authentication for Routing Protocols (KARP) working group of the Internet Engineering Task Force: RKMP, MRKM, and MaRK. These KMPs are designed to have better applicability for general routing protocols. However, the security of these protocols has not been validated. In this thesis, we have summarized the necessary conditions for security of routing protocols. We have analyzed the security aspects of RKMP, MRKM, and MaRK, by formally validating those protocols using the AVISPA modeling tool. This has shown that these KMPs meet the necessary security requirements.

The application of virtual simulation technology promotes the reform of experimental teaching methods in colleges and universities to provide reliable support for cultivating students’ professional engineering application ability and improve the overall quality of talent training. Based on real projects, this virtual simulation experiment project adopts the trinity teaching method of ‘virtual environment, actual problems, real ability’. And it makes full use of natural language processing and other AI technology and software technology to provide students with requirement analysis experiments that are very close to reality. The practical environment has played a multifaceted effect and solved the students’ neglect of the importance of requirement analysis.