Parul Sharma

Arnaud Joly, Marco Nicolis, Ekaterina Peterova et al. · amazon-science

We present a scalable method to produce high quality emphasis for text-to-speech (TTS) that does not require recordings or annotations. Many TTS models include a phoneme duration model. A simple but effective method to achieve emphasized speech consists in increasing the predicted duration of the emphasised word. We show that this is significantly better than spectrogram modification techniques improving naturalness by $7.3\%$ and correct testers' identification of the emphasized word in a sentence by $40\%$ on a reference female en-US voice. We show that this technique significantly closes the gap to methods that require explicit recordings. The method proved to be scalable and preferred in all four languages tested (English, Spanish, Italian, German), for different voices and multiple speaking styles.

Parul Sharma, Dr. Anup Girdhar

Though, IPv6 has presented a long list of features that will actually change the entire networking environment, it still represents a very small proportion of Internet traffic. One of the major reasons behind its partial acceptance is its security, as these features were incorporated in IPv6 just to enhance its overall performance and quality of service, thereby neglecting its security part. One such feature is Stateless Address Auto Configuration or simply SLAAC, which have undoubtedly reduced a lot of overhead in configuring networks, but on the same time it has challenged the security of IPv6 networks. This research work, therefore targets at proposing some security policies to mitigate the risks associated with SLAAC, by understanding its working scenario and trying to create the possible attack vector to highlight its security concerns. Hence, the implementation of these policies will directly add security to networks and make them resistant to SLAAC based attacks.