SCANMail: browsing and searching speech data by content

Published 3 September 2001

Julia Hirschberg, Michiel Bacchiani, Don Hindle, Phil Isenhour, A. E. Rosenberg, Litza Stark

DOI10.21437/eurospeech.2001-336

Citations33

TL;DR

SCANMail is described, 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.

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.

Keywords

Computer Science

Computer Speech & LanguageMaximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models

2,210 Citations1995C.J. Leggetter, Philip C. Woodland

An important feature of the method is that arbitrary adaptation data can be used—no special enrolment sentences are needed and that as more data is used the adaptation performance improves.

Computer Speech & LanguageMaximum likelihood linear transformations for HMM-based speech recognition

1,490 Citations1998Mark Gales

The paper compares the two possible forms of model-based transforms: unconstrained, where any combination of mean and variance transform may be used, and constrained, which requires the variance transform to have the same form as the mean transform.

IEEE Transactions on Speech and Audio ProcessingSemi-tied covariance matrices for hidden Markov models

538 Citations1999Mark Gales

A new form of covariance matrix which allows a few "full" covariance matrices to be shared over many distributions, whilst each distribution maintains its own "diagonal" covariancy matrix is introduced.

The Journal of the Acoustical Society of AmericaThe AT&T Next-Gen TTS System

178 Citations1999Mark C. Beutnagel, Alistair Conkie +3 more

The new AT&T TTS system for general U.S. English text is based on best‐choice components picked from the AT&t Flextalk TTS, the Festival System from the University of Edinburgh, and ATR’s CHATR system, and each decision made during the research and development phase was based on formal subjective evaluations.

The Journal of the Acoustical Society of AmericaVocal tract normalization in speech recognition: Compensating for systematic speaker variability

84 Citations1995Jordan Cohen, Terri Kamm +1 more

The SWITCHBOARD corpus, studied during the 1994 CAIP workshop [Frontiers in Speech Processing Workshop II, CAIP (August 1994), an attempt was made to compensate for the systematic variability due to different vocal tract lengths of various speakers.

View PDF

All talk and all action

28 Citations1998Steve Whittaker, Julia Hirschberg +1 more

Three problems users experience in managing their voicemail are identified: scanning, information extraction and search and recommendations about how voicemail might be redesigned to better address these problems and support these strategies are made.

View PDF

Play it again

22 Citations1998Steve Whittaker, Julia Hirschberg +1 more

A laboratory study of speech archive browsing using a GUI found that while users learnt the overall layout of topics in the archive, they experienced major problems in learning the internal structure of archival topics.

Automatic transcription of voicemail at AT&T

15 Citations2002Michiel Bacchiani

Reports on the automatic transcription accuracy of voicemail messages shows that vocal tract length normalization and adaptation using linear transformations, proven to improve accuracy on the Switchboard task, provide similar accuracy improvements on this task.

Foldering voicemail messages by caller using text independent speaker recognition

8 Citations2000A. E. Rosenberg, S. Parthasarathy +2 more

A system which automatically sends voicemail messages into caller folders using text independent speaker recognition techniques using Gaussian mixture models to train and adapt caller models is described.