This paper describes a multi-microphone multi-language acoustic corpus being developed under the EC project Distant-speech Interaction for Robust Home Applications (DIRHA). The corpus is composed of several sequences obtained by convolution of dry acoustic events with more than 9000 impulse responses measured in a real apartment equipped with 40 microphones. The acoustic events include in-domain sentences of different typologies uttered by native speakers in four different languages and non-speech events representing typical domestic noises. To increase the realism of the resulting corpus, background noises were recorded in the real home environment and then added to the generated sequences. The purpose of this work is to describe the simulation procedure and the data sets that were created and used to derive the corpus. The corpus contains signals of different characteristics making it suitable for various multi-microphone signal processing and distant speech recognition tasks.

The EC-funded project DICIT developed distant-talking interfaces for interactive TV. The final DICIT prototype system processes multimodal user input by speech and remote control. It was designed to understand both natural language and command-and-control-style speech input. We conducted an evaluation campaign to examine the usability and performance of the prototype. The task-oriented evaluation involved naive test persons and consisted of a subjective part with a usability questionnaire and an objective part. We used three groups of objective metrics to assess the system: one group related to speech component performance, one related to interface design and user awareness, and a final group related to task-based effectiveness and usability. These metrics were acquired with a dedicated transcription and annotation tool. The evaluation revealed a quite positive subjective assessments of the system and reasonable objective results. We report how the objective metrics helped us to determine problems in specific areas and to distinguish design-related issues from technical problems. The metrics computed over modality-specific groups also show that speech input gives a usability advantage over remote control for certain types of tasks.

This paper describes a multichannel acoustic data collection recorded under the European DICIT project, during the Wizard of Oz (WOZ) experiments carried out at FAU and FBK-irst laboratories. The scenario is a distant-talking interface for interactive control of a TV. The experiments involve the acquisition of multichannel data for signal processing front-end and were carried out due to the need to collect a database for testing acoustic pre-processing algorithms. In this way, realistic scenarios can be simulated at a preliminary stage, instead of real-time implementations, allowing for repeatable experiments. To match the project requirements, the WOZ experiments were recorded in three languages: English, German and Italian. Besides the user inputs, the database also contains non-speech related acoustic events, room impulse response measurements and video data, the latter used to compute 3D labels. Sessions were manually transcribed and segmented at word level, introducing also specific labels for acoustic events.