J. Hirschberg, S. Whittaker, D. Hindle, F. Pereira, and A. Singhal, "Finding information in audio: a new paradigm for audio browsing and retrieval, " in Proc. ESCA ETRW Workshop Acessing Information in Spoken Audio, (Cambridge), pp. 117--122, 1999. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Sub-Word-Based Language Models for Speech Recognition.. - Larson Self-citation (Information) (Correct)
....user can skim the list without having to listen to each selection; audio is only scanable in (near) real time. The transcript can also be stored compactly and the original recordings may no longer even be necessary. Representing retrieval results for spoken audio can be tricky. 23] and especially [8] address this issue. The disadvantage of creating a transcription before doing retrieval, is that a recognizer processing speech in transcription mode aims to minimize word error rate (WER) and this is not necessarily good for IR. WER concerns only the best hypothesis that the recognizer ....
J. Hirschberg, S. Whittaker, D. Hindle, F. Pereira and A. Singhal, Finding information in audio: A new paradigm for audio browsing/retrieval, ESCA ETRW workshop Accessing information in spoken audio, Cambridge, April 1999. http://svr-www.eng.cam.ac.uk/~ajr/esca99/
The Rules Behind Roles: Identifying Speaker Role in .. - Barzilay, Collins, .. (2000) (1 citation) Self-citation (Hirschberg Whittaker) (Correct)
....structure. Both anchors and journalists present explicit structural information. Speaker transitions also yield structural information: when a journalist stops speaking, this is a strong cue that a story has ended. This technique is being developed in the context of an audio browsing project SCAN (Hirschberg et al. 1999) on the DARPA Broadcast News corpus. We present a machine learning algorithm for speaker role identification from audio data. The algorithm s input is ASR transcriptions from All Things Considered programs, with boundaries between speakers identified, but the identity of speakers unknown. The ....
Hirschberg, J.; Whittaker, S.; Hindle, D.; Pereira, F.; and Singhal, A. 1999. Finding information in audio: A new paradigm for audio browsing and retrieval. In Proceeding of the ESCA ETRW Workshop.
The Thisl System For Indexing And Retrieval Of Broadcast News - Steve Renals David (1999) (Correct)
No context found.
J. Hirschberg, S. Whittaker, D. Hindle, F. Pereira, and A. Singhal, "Finding information in audio: a new paradigm for audio browsing and retrieval, " in Proc. ESCA ETRW Workshop Acessing Information in Spoken Audio, (Cambridge), pp. 117--122, 1999.
Multimedia Information Access Using Multiple Speaker.. - Viswanathan, Maali.. (2000) (Correct)
No context found.
Hirschberg, J., Whittaker, S., Hindle, D., Periera, F. & Singhal, A. (1999). Finding Information in Audio: A New Paradigm for Audio Browsing and Retrieval. In Proceedings of the ESCA Tutorial and Research Workshop.
Minimizing Word Error Rate in Textual Summaries of Spoken.. - Zechner, Waibel (2000) (6 citations) (Correct)
No context found.
Julia Hirschberg, Steve Whittaker, Don Hindle, Fernando Pereira, and Amit Singhal. 1999. Finding information in audio: A new paradigm for audio browsing/retrieval. In Proceedings of the ESCA workshop: Accessing information in spoken audio, pages 117--122. Cambridge, UK, April.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC