The acoustic startle response (ASR) elicited by 110 dB 10-ms pulses was studied in relation to pain sensitivity in mouse lines selectively bred for high (HA) and for low (LA) swim analgesia. The magnitudes of ASR, similarly as hot-plate latencies, differed between the lines in the rank order HA is greater than unselected controls (C) greater than LA. The animals' nociception did not change afte...

Almost all current automatic speech recognition (ASR) systems use a similar paradigm [3, 51, 52], which will be referred to here briefly as the ‘invariant approach’. Despite intensive research, ASR performance is still at least an order of magnitude lower than that of human speech recognition (HSR). The difficulties encountered in improving ASR performance, in combination with the awareness tha...

Although great progress has been made towards understanding the role of abscisic acid (ABA) and sucrose in fruit ripening, the mechanisms underlying the ABA and sucrose signalling pathways remain elusive. In this study, transcription factor ABA-stress-ripening (ASR), which is involved in the transduction of ABA and sucrose signalling pathways, was isolated and analysed in the nonclimacteric fru...

Spoken term detection (STD) from oral presentations is addressed. Specifically, we regard STD as a line detection problem in an image file, in which each pixel holds a syllabledistance between query term and automatic speech recognition (ASR) results. Since such kind of image file essentially includes ASR errors, line detection in noisy image should be investigated. In this paper, we propose li...

Speech translation is conventionally carried out by cascading an automatic speech recognition (ASR) and a statistical machine translation (SMT) system. The hypotheses chosen for translation are based on the ASR system’s acoustic and language model scores, and typically optimized for word error rate, ignoring the intended downstream use: automatic translation. In this paper, we present a coarset...

This paper proposes a named entity recognition (NER) method for speech recognition results that uses confidence on automatic speech recognition (ASR) as a feature. The ASR confidence feature indicates whether each word has been correctly recognized. The NER model is trained using ASR results with named entity (NE) labels as well as the corresponding transcriptions with NE labels. In experiments...

This paper presents an improved wavelet-based dereverberation method for automatic speech recognition (ASR). Dereverberation is based on filtering reverberant wavelet coefficients with the Wiener gains to suppress the effect of the late reflections. Optimization of the wavelet parameters using acoustic model enables the system to estimate the clean speech and late reflections effectively. This ...

This paper presents a method for the named entity recognition (NER) of speech data that uses automatic speech recognition (ASR) confidence as a feature that indicates whether each word is correctly recognized. An NER model is trained using ASR results with named entity (NE) labels to include an ASR confidence feature as well as corresponding transcriptions with NE labels. Experiments using supp...