Lipper: Synthesizing Thy Speech using Multi-View Lipreading
This work addresses the challenge of making lipreading more versatile and language-independent for applications like surveillance and video conferencing, though it appears incremental as it builds on existing lipreading concepts with a multi-view approach.
The paper tackles the problem of generating speech from silent videos by proposing Lipper, a multi-view lipreading system that treats it as a regression task rather than text classification, resulting in improved speech reconstruction over single-view methods and demonstrating real-time audio production with user studies on comprehensibility.
Lipreading has a lot of potential applications such as in the domain of surveillance and video conferencing. Despite this, most of the work in building lipreading systems has been limited to classifying silent videos into classes representing text phrases. However, there are multiple problems associated with making lipreading a text-based classification task like its dependence on a particular language and vocabulary mapping. Thus, in this paper we propose a multi-view lipreading to audio system, namely Lipper, which models it as a regression task. The model takes silent videos as input and produces speech as the output. With multi-view silent videos, we observe an improvement over single-view speech reconstruction results. We show this by presenting an exhaustive set of experiments for speaker-dependent, out-of-vocabulary and speaker-independent settings. Further, we compare the delay values of Lipper with other speechreading systems in order to show the real-time nature of audio produced. We also perform a user study for the audios produced in order to understand the level of comprehensibility of audios produced using Lipper.