Improving speech playback using time-compression and speech recognition

Despite the ready availability of digital recording technology and the continually decreasing cost of digital storage, browsing audio recordings remains a tedious task. This paper presents evidence in support of a system designed to assist with information comprehension and retrieval tasks from a large collection of recorded speech. Two techniques are employed to assist users with these tasks. First, a speech recognizer creates necessarily errorladen transcripts of the recorded speech. Second, audio playback is time-compressed using the SOLAFS technique. When used together, subjects are able to perform comprehension tasks with more speed and accuracy. Author Keywords Speech recognition, time-compressed audio, information retrieval. ACM Classification Keywords H.5.2. Information interfaces and presentation (e.g., HCI): User Interfaces, Voice I/O; I.2.7. Natural Language Processing: Speech recognition and synthesis

• Type: Conference
• Year: 2004
• Where: CHI
• Authors: Sunil Vemuri, Philip DeCamp, Walter Bender, Chris Schmandt
• Keywords: CHI 2004, Comprehension Tasks, Human Computer Interaction, Keywords Speech Recognition, Speech Recognizer