Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes an algorithm to learn a distance metric for time series alignment. The proposed method falls into the structured output prediction framework, and is solved by a combination of convex optimization and dynamic programming. The method is evaluated on synthetic and realistic audio alignment tasks, and demonstrates significant improvement over baseline methods. Overall, this paper presents an interesting method for a real problem faced by practitioners dealing with time-series alignment tasks. The paper is generally well written and easy to follow, although a few points could be stated more clearly.