The effects of irrelevant speech were examined on a range of memory tasks. A missing-item task, which relied on a nonserial strategy for recall, proved less sensitive to the effects of irrelevant speech than one calling on memory for serial order. The finding that the effect of irrelevant speech both on a recognition task and on a paired-associates task was modified significantly by articulator...

This paper describes the development of the cu-con system which participated in the 1996 ARPA Hub 4 Evaluations. The system is based on Abbot, a hybrid connectionist-HMM large vocabulary continuous speech recognition system developed at the Cambridge University Engineering Department [4]. The Hub 4 Evaluation task involves the transcription of broadcast television and radio news programmes. Thi...

This paper describes the development of the cu-con system which participated in the 1996 ARPA Hub 4 Evaluations. The system is based on Abbot, a hybrid connec-tionist-HMM large vocabulary continuous speech recognition system developed at the Cambridge University Engineering Department 4]. The Hub 4 Evaluation task involves the transcription of broadcast television and radio news programmes. Thi...

To cope with complicated interference scenarios in realistic acoustic environment, supervised deep neural networks (DNNs) are investigated to estimate different user-defined targets. Such techniques can be broadly categorized into magnitude estimation and time-frequency mask techniques. Further, the such as Wiener gain estimated directly or derived by power spectral density (PSD) signal-to-inte...

Speech recognition applications always face the problem of changing vocabulary and functionality. The use of speech recognition systems will become more attractive if the system user is able to define or redefine the task himself in a suitable manner. Modelling a new task normally requires the experience of a human expert and a lot of time. Aditionally, the expert always has to be contacted if ...

Design problem solving is a complex activity involving a number of subtasks and a number of alternative methods potentially available for each subtask. The structure of tasks has been a key concern of recent research in task-oriented methodologies for knowledge-based systems (Chandrasekaran 1986; Clancey 1985; Steels 1990; McDermott 1988). One way to conduct a task analysis is to develop a task...

BACKGROUND Even today the reliable diagnosis of the prodromal stages of Alzheimer's disease (AD) remains a great challenge. Our research focuses on the earliest detectable indicators of cognitive decline in mild cognitive impairment (MCI). Since the presence of language impairment has been reported even in the mild stage of AD, the aim of this study is to develop a sensitive neuropsychological ...

This paper deals with the issue of language model selection based on the analysis of data collection for spontaneous speech in Japanese in the travel arrangement task which contains five different subtasks. The procedure of transcription and segmentation of the Japanese spontaneous speech in Romanized transcription is described. The use of topic-dependent separated language model were evaluated...

We explore multimodal recognition by combining visual lipreading with acoustic speech recognition. We show that combining the visual and acoustic clues of speech improves the recog­ nition performance significantly especially in noisy environment. We achieve this with a hybrid speech recognition architecture, consisting of a new visual learning and tracking mechanism, a channel robust acoustic ...