An Efficient Cascaded Filtering Retrieval Method for Big Audio Data

Abstract

Fast audio retrieval is crucial for many important applications and yet demanding due to the high dimension nature and increasingly larger volume of audios in the internet. Although audio fingerprinting can greatly reduce its dimension while keeping audio identifiable, the dimension of audio fingerprints is still too high to scale up for big audio data. The tradeoff between the accuracy and the efficiency prevents the further reducing of the dimension of fingerprints. This paper proposes a multi-stage filtering strategy for audio retrieval, with the beginning stages focusing on speed up by using a middle fingerprint with much smaller size to quickly filtering the most likely audios, and the ending stages emphasizing on accuracy by applying an accurate and robust fingerprint on the small set of the most likely audios. A notion called middle fingerprint is devised with considerable small dimension for quickly filtering out most irrelevant audios. A matching algorithm is developed to reduce the computational complexity by comparing the samples at fixed interval of two audios with thresholds. By using the middle fingerprint, audio retrieval can get a speed gain of 12 times on average compared with the Fibonacci Hashing retrieval. By combing the Fibonacci hashing algorithm with the middle filtering retrieval and the matching algorithm, we propose an efficient cascaded filtering retrieval methods, which can further improve the retrieval by 250 times on average. After applying MP3 conversion, resampling, and random shearing, the recall rates of the method are all above 99.47%, and the theoretical accuracy is close to 100%.

Big Data driven Product Design: A Survey

“…Big audio data [231] is information with sound or voice. The customer center brings together users' complaints, inquiries, and suggestions during the product service cycle [232].…”

“…Although video data is useful, manual viewing is time-consuming and only suited for small data volume scenes. In comparison, intelligent video analysis can realize motion detection, video summarization, video retrieval, color detection, object detection, emotion recognition, etc., [244,245,231,246] independent of human engagements. Intelligent video analysis makes it possible to apply big video data in user requirement acquisition, user behavior observation, experience improvement, and product virtual display.…”

Encrypted speech retrieval based on long sequence Biohashing

“…For large-scale feature index, the key problem is to improve the computational efficiency of massive speech search. By changing the index structure or compressing the original features, such as score fusion [18], Gaussian-LDA (late Dirichlet allocation) [8], Fibonacci hash [29], two stage sparse phase retrieval (TSPR) [10], query likelihood model (QLM) [22], perceptual hash and other methods, this problem can be effectively solved.…”