Audio search engine

About: Audio search engine is a research topic. Over the lifetime, 12 publications have been published within this topic receiving 895 citations.

Acoustic Lexemes for Organizing Internet Audio

Abstract: In this article, a method is proposed for automatic fine-scale audio description that draws inspiration from ontological sound description methods such as Shaeffer's Objets Sonores and Smalley's Spectromorphology. The goal is complete automation of audio description at the level of sound objects for indexing and retrieving sound segments within Internet audio documents. To automatically segment audio documents into acoustic lexemes, a hidden Markov model is employed. It is demonstrated that the symbol stream of cluster labels, generated by the Viterbi algorithm, constitutes a detailed description of audio as a sequence of spectral archetypes. The ASCII base-64 encoding scheme maps cluster indices to one-character symbols that are segmented into 8-gram sequences for indexing in a relational database. To illustrate the methods, the essential components of an audio search engine are described: the automatic cataloguer, the retrieval engine and the query language. The results of experiments that test the accu...

ASEKS: A P2P Audio Search Engine Based on Keyword Spotting

Abstract: Currently, most search engines are text-based and their structures are centralized. These kinds of engine are sufficient for searching text information in Internet. However, while searching audio resource, an efficient content-based audio search engine is required. In this paper, we demonstrate an audio search engine ASEKS based on keyword spotting technology in the peer-to-peer (P2P) network. The indexing sub-model spots information in local audio files and generates indices for later query; and the P2P networks distributes the query and gathers the results. ASEKS supports scalability and avoids the bottleneck of network load that usually exists in centralized architecture. The average accuracy of the keyword spotting sub-model is 88.4% in detection rate on the 5.267 false alarm per keyword per hour.

A Semantic and Content-Based Search User Interface for Browsing Large Collections of Foley Sounds

Abstract: Sound designers select the sounds they use among massive collections of recordings. They usually rely on text-based queries to narrow down a subset from these collections when looking for specific content. However, when it comes to unknown collections, this approach can fail to precisely retrieve files according to their content. We investigate an audio search engine that associates content-based features and semantic meta-data using Apache Solr deployed in a fully integrated server architecture. In order to facilitate the task of browsing the sounds, we also propose a search user interface in which the user can perform both text-based queries and visual browsing in a window where sounds are organized according to their audio features. A preliminary evaluation of the performances helped to optimize the parameters of the system.

AROOOGA: An Audio Search Engine for theWorldWideWeb

Abstract: Existing search engines use web crawlers to gather web pages. The extracted information is used to build indexes, which are later used to answer user queries. This approach is useful for general queries, but ignores the special properties of sound files, making it difficult to accurately locate specific sound files on the web. AROOOGA, or the Articulated Resource for Obsequious Opinionated Observations into Gathered Audio, is a web crawling system designed specifically to find and analyze audio resources on the web. The AROOOGA web crawler uses both audio information and the associated web pages to produce higher-quality search indexes for music information retrieval. Information about sound files on the web is discussed, and some preliminary search results are included.

Tag Based Audio Search Engine

Abstract: The volume of the music database is increasing day by day. Getting the required song as per the choice of the listener is a big challenge. Hence, it is really hard to manage this huge quantity, in terms of searching, filtering, through the music database. It is surprising to see that the audio and music industry still rely on very simplistic metadata to describe music files. However, while searching audio resource, an efficient “Tag Based Audio Search Engine” is necessary. The current research focuses on two aspects of the musical databases 1. Tag Based Semantic Annotation Generation using the tag based approach.2. An audio search engine, using which the user can retrieve the songs based on the users’ choice. The proposed method can be used to annotation and retrieve songs based on musical instruments used , mood of the song, theme of the song, singer, music director, artist, film director, instrument, genre or style and so on.