Susanne Burger

Syllable detection in read and spontaneous speech

Automatic syllable detection is an important task when analysing very large speech corpora in order to answer questions concerning prosody, rhythm, speech rate, speech recognition and synthesis. A new method for automatic detection of syllable nuclei is presented. Two large spoken language corpora (PhonDatII, Verbmobil) were labelled by three phoneticians and then used to adjust the key parameters of the algorithm and to evaluate its error rate. Additionally, parts of the corpora were used to test the inter- and intra-individual consistency of the transcribers. The evaluation of the algorithm currently shows an error rate of 12.87% for read speech and 21.03% for spontaneous speech. The inter-individual consistency of 95.8% might be considered as an upper limit for any automatic detection method.

Spoken Dialog Challenge 2010

This paper describes the 2010 Spoken Dialog Challenge, a multi-site challenge to help investigate different spoken dialog system and evaluation techniques. The aim of the Challenge is to bring together multiple implementations of the same dialog task and deploy them in uncontrolled real user conditions and then make the results available for common evaluation techniques. This paper gives an overview of teh Challenge itself and the task, and presents the results for the “controlled task” part of the evaluation. The paper also discusses the infrastructure and organizational issues encountered and the solutions that made this challenge possible.

Verbmobil Data Collection and Annotation

Verbmobil data collection had to satisfy the different requirements for data quality and annotation level for each project partner. This chapter describes the different user grouns, their data demands and how the data collection group solved these issues.

Eliciting natural speech from non-native users: collecting speech data for LVCSR

In this paper, we discuss the design of a database of recorded and transcribed read and spontaneous speech of semi-fluent, strongly-accented non-native speakers of English. While many speech applications work best with a recognizer that expects native-like usage, others could benefit from a speech recognition component that is forgiving of the sorts of errors that are not a barrier to communication; in order to train such a recognizer a database of non-native speech is needed. We examine how collecting data from non-native speakers must necessarily differ from collection from native speakers, and describe work we did to develop an appropriate scenario, recording setup, and optimal surroundings during recording.

Incremental Multimodal Query Construction for Video Search

Recent improvements in content-based video search have led to systems with promising accuracy, thus opening up the possibility for interactive content-based video search to the general public. We present an interactive system based on a state-of-the-art content-based video search pipeline which enables users to do multimodal text-to-video and video-to-video search in large video collections, and to incrementally refine queries through relevance feedback and model visualization. Also, the comprehensive functionalities enhance a flexible formulation of multimodal queries with different characteristics. Quantitative and qualitative analysis shows that our system is capable of assisting users to incrementally build effective queries over complex event topics.

Perceptual Component Evaluation and Data Collection

Systematic evaluation is essential to drive the rapid progress of a broad range of audiovisual perceptual technologies. Within the CHIL project, such evaluations were undertaken on an annual basis, so that improvements could be measured objectively, and different approaches compared and assessed.