2020/05/21 by Viet Anh Trinh, Michael Mandel, Michael I Mandel
Computer Science · Mathematics · #Artificial intelligence #Baseline (sea) #Benchmark (surveying) #Computer science #Domain Adaptation and Few-Shot Learning #Explainable Artificial Intelligence (XAI) #Mathematics #Metric (unit) #Natural language processing #Noise (video) #Pattern recognition (psychology) #Scale (ratio) #Sequence (biology) #Speech recognition #Topic Modeling #Utterance #Word (group theory) #cs.CV #cs.LG #cs.SD
paper · pdf · doi:10.21437/interspeech.2020-2883
published as Proceedings of Interspeech 2020 · submitted to INTERSPEECH 2020
arxiv created 2020/05/21 · openalex publication_date 2020/10/25 · arxiv updated 2020/12/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
In this paper, we propose a metric that we call the structured saliency benchmark (SSBM) to evaluate importance maps computed for automatic speech recognizers on individual utterances. These maps indicate time-frequency points of the utterance that are most important for correct recognition of a target word. Our evaluation technique is not only suitable for standard classification tasks, but is also appropriate for structured prediction tasks like sequence-to-sequence models. Additionally, we use this approach to perform a large scale comparison of the importance maps created by our previously introduced technique using "bubble noise" to identify important points through correlation with a baseline approach based on smoothed speech energy and forced alignment. Our results show that the bubble analysis approach is better at identifying important speech regions than this baseline on 100 sentences from the AMI corpus.