History-based visual mining of semi-structured audio and text

Proceedings of the 9th ACM SIGCHI New Zealand Chapter's International Conference on Human-Computer Interaction: Design Centered

Masoodian

Rogers

2008

As performance gains in automatic speech recognition systems plateau, improvements to existing applications of speech recognition technology seem more likely to come from better user interface design than from further progress in core recognition components. Among all applications of speech recognition, the usability of systems for transcription of spontaneous speech is particularly sensitive to high word error rates. This paper presents a series of approaches to improving the usability of such applications. We propose new mechanisms for error correction, use of contextual information, and use of 3D visualisation techniques to improve user interaction with a recogniser and maximise the impact of user feedback. These proposals are illustrated through several prototypes which target tasks such as: off-line transcript editing, dynamic transcript editing, and real-time visualisation of recognition paths. An evaluation of our dynamic transcript editing system demonstrates the gains that can be made by adding the corrected words to the recogniser's dictionary and then propagating the user's corrections.

Section: Other Techniquesmentioning

confidence: 99%

Interactive visualisation techniques for dynamic speech transcription, correction and training

Proceedings of the 9th ACM SIGCHI New Zealand Chapter's International Conference on Human-Computer Interaction: Design Centered

Masoodian

Rogers

2008

“…The graph grows vertically with the number of streams, potentially impairing the user's ability to recognise concurrent events (across streams) and exclusively inactive intervals. For certain tasks, such as browsing of meeting recordings, being able to recognise and locate these kinds of events can be crucial [2]. The temporal mosaic was initially developed to address these issues.…”

Section: The Temporal Mosaicmentioning

confidence: 99%

Visualisation of Parallel Data Streams with Temporal Mosaics

2007 11th International Conference Information Visualization (IV '07)

Masoodian

2007

“…Inversely, increasing the tolerance value may increase recall but at the expense of including irrelevant information. A detailed description of paragraph level retrieval and browsing can be found in [14]. Fig.…”

Section: Paragraph-based Retrievalmentioning

confidence: 99%

Navigating Multimodal Meeting Recordings with the Meeting Miner

Bouamrane

Flexible Query Answering Systems

2006

Abstract. We present Meeting Miner, a multimodal meeting browser for navigating recordings of online text and speech collaborative meetings. Meetings are recorded through a collaborative writing environment specially designed to capture participants activities. This information, usually lost in common recordings of multimodal meetings, offers novel possibilities for indexing, navigation and information retrieval in archived meetings. Meeting Miner uses temporal information from the logs of actions captured on self-contained information items (paragraphs of text) to uncover potential information links between these semantic data units. A novel space-based action navigation scheme is presented. Keywords and topic search as well as more advanced queries can be performed by the system. We illustrate the system navigation modalities with several browsing examples.