Let's Hear It for Audio Mining

T he Web, databases, and other digitized information store-houses contain a growing volume of audio content. Sources include newscasts, sporting events, telephone conversations, recordings of meetings, Webcasts, documentary archives such as the Visual History Foundation's interviews with Holocaust survivors (http://www.vhf. org), and media files in libraries. Users want to make the most of this material by searching and indexing the digitized audio content. In the past, companies had to create and manually analyze written transcripts of audio content because using computers to recognize, interpret, and analyze digitized speech was difficult. However, the development of faster microprocessors , larger storage capacities, and better speech-recognition algorithms has made audio mining easier. Now, the technology is on the verge of becoming a powerful tool that could help many organizations. For example, companies could use audio mining to analyze customer-service and help-desk conversations or even voice mail. Law enforcement and intelligence organizations could use the technology to analyze intercepted phone conversations. Public relations firms could use it to analyze news broadcasts to find coverage of clients. Broadcast companies like CNN and Radio Free Asia are already using audio mining to quickly retrieve important background information from previous broadcasts when new stories break. And a US prison is using ScanSoft's audio mining product to analyze recordings of prisoners' phone calls to identify illegal activity. Several companies such as BBN Technologies (http://www.bbn.com), Fast-Talk Communications (http:// www.fast-talk.com), IBM, and Scan-Soft have released audio mining software , and industry observers expect the number of products to increase during the next few years. However, audio mining's accuracy levels are still relatively low, and some products are expensive, with some high-end software packages costing more than $100,000 for a full-scale deployment. Audio mining, also called audio searching, takes a text-based query and locates the search term or phrase in an audio file. This helps users by, for example, letting them quickly get to specific places in a recorded conversation or determine when a company is mentioned in a newscast. Audio indexing uses speech recognition to analyze an entire file and produce a searchable index of content-bearing words and their locations. This is critical because audio content is in a binary format that is otherwise not readily searchable, explained Robert Weideman, ScanSoft's chief marketing officer. Indexing audio content thus enables searching, said Jeff Karnes, a group product manager for Virage, an audio mining vendor. There are two main approaches to audio …