This paper explores a new approach to speech recognition in which sub-word units are modeled in terms of linguistic features. Specifically, we have adopted a scheme of modeling separately the manner and place of articulation for these units. A novelty of our work is the use of a generalized definition of place of articulation that enables us to map both vowels and consonants into a common lingu...

Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching. In this paper, we propose some modifications to the traditional measures based on word embeddings for these two metrics. The evaluation results show that our...

We propose a novel framework to detect and recognize outof-vocabulary (OOV) words in automated speech recognition (ASR). In the proposed framework a hybrid language model combining words and sub-word units is incorporated during ASR decoding then three different OOV words recognition methods are applied to generate OOV word hypotheses. Specifically, dictionary lookup, morphological composition,...

In this paper we present a case study of media reporting about medical technology issues. We discuss two incidents involving human error with medical devices that resulted in infant deaths, and their relevance for the medical device design and mobile health communities. Our analysis into the language and discourses of news reporting shows that the news narratives of these incidents emphasise hu...

This paper deals with unsupervised feature-based speaker adaptation techniques. The goal is to design an optimal adaptation approach for improving the recognition accuracy of a LVCSR system developed for automatic transcription of large archives of spoken Czech (e.g. the archive of the parliament talks, historical archives of Czech broadcast stations, etc.) For this purpose, several modificatio...

Rollen als Teile eines Vorgehensmodells dienen dazu, Aufgaben und Verantwortlichkeiten eindeutig und optimal Personen zuzuweisen. Da das Requirements Engineering und Management (RE&M) wichtig ist, gibt es bei vielen jedoch nicht allen Vorgehensmodellen eine oder mehrere Rollen, die das RE&M durchführen. Tatsächlich ergeben sich in der Praxis einige Schwierigkeiten bei der Arbeit im RE&M aufgrun...

This paper deals with speaker adaptation techniques well suited for the task of online subtitling. Two methods are briefly discussed, namely MAP adaptation and fMLLR. The main emphasis is laid on the description of improvements involved in the process of adaptation subject to the time requirements. Since the adaptation data are gathered continuously, simple modifications of the accumulated stat...

We investigate recognition of spontaneous speech using the focus of visual attention as a secondary cue to speech. In our experiment we collected a corpus of eye and speech data where one participant describes a geographical map to another while having their eye movements tracked. Using this corpus we characterise the coupling between eye movement and speech. Speech recognition results are pres...

We describe a data collection consisting of task-oriented human-human conversations in a simulated ASR channel in which the WER is systematically varied. We find that users infrequently give a direct indication of having been misunderstood; levels of expert “initiative” increase with WER primarily due to increased grounding activity; and asking task-related questions appears to be a more succes...