SCANMail: browsing and searching speech data by content

TLDR

Increasing amounts of public, corporate, and private audio data are available, yet their usefulness is limited by the lack of tools for browsing and searching. This paper introduces SCANMail, a system that uses automatic speech recognition, information retrieval, and information extraction to enable users to browse and search voicemail messages by content via a graphical interface. SCANMail includes a client with note‑taking, browsing, and querying features, a CallerID server that suggests caller names from acoustic models trained on user feedback, and an email server that forwards the original message and its transcription to a user‑specified address.

Abstract

Increasing amounts of public, corporate, and private audio data are available for use, but limited in usefulness by the lack of tools to permit their browsing and search. In this paper, we describe SCANMail, a system that employs automatic speech recognition, information retrieval, information extraction, and human computer interaction technology to permit users to browse and search their voicemail messages by content through a graphical user interface interface. The SCANMail client also provides note-taking capabilities as well as browsing and querying features. A CallerId server also proposes caller names from existing caller acoustic models and is trained from user feedback. An Email server sends the original message plus its transcription to a mailing address specified in the user’s profile.