Output Sentences Research Articles

Turing Test-Based Evaluation of an Experimental System for Generation of Casual English Sentences from Regular English Input

This paper proposes an experimental system for generating slang-style casual English sentences from regular English input using a phonetic database approach, primarily as an AI task, with real-life applications such as social media marketing. An original database consisting of multiple candidates of casual English phonemes was constructed, and linguistic analysis of Twitter data used to establish the optimum frequency of slang tokens per sentence. The human-likeness and legibility of output sentences of the experimental system were evaluated using an experiment based on the classical definition of the Turing test, in which fifty human evaluators attempted to distinguish sentences produced by the system from genuine humanauthored sentences. The experiment results demonstrated that the gap in human-likeness scores between the “human” and “machine” sentences was small, and that some “machine” sentences actually outperformed several of the “human sentences.” The “machine” sentences’ average score of 3.1 on a 5-point scale, where 3 indicated complete uncertainty of whether the sentences were human-authored or machine-authored, can be considered a pass of the Turing test in the established definition. In this paper, we describe the potential approaches to the task, the construction of the phonetic database and the proposed system, and discuss the evaluation results.

Identification of Soundbite and Its Speaker Name Using Transcripts of Broadcast News Speech

This article presents a pipeline framework for identifying soundbite and its speaker name from Mandarin broadcast news transcripts. Both of the two modules, soundbite segment detection and soundbite speaker name recognition, are based on a supervised classification approach using multiple linguistic features. We systematically evaluated performance for each module as well as the entire system, and investigated the effect of using speech recognition (ASR) output and automatic sentence segmentation. We found that both of the two components impact the pipeline system, with more degradation in the entire system performance due to automatic speaker name recognition errors than soundbite segment detection. In addition, our experimental results show that using ASR output degrades the system performance significantly, and that using automatic sentence segmentation greatly impacts soundbite detection, but has much less effect on speaker name recognition.

AIS에 의한 선박거동의 실시간 모니터링

This paper describes on the real-time tracking of ship's dynamic behavior by AIS information in the coastal waters. The AIS data was received at a land station by using the antenna of AIS receiver mounted on the rooftop of the laboratory, Pukyong National University (PKNU), Busan, Korea, and stored as a NMEA format of serial output sentence of VDM(VHF Data-Link Message) and displayed on the ENC(Electronic Navigational Chart) of a PC-based ECDIS. In this study, the AIS receiver was mainly used to obtain the dynamic information that is necessary to evaluate and track the movement situation of training ship "KAYA" of PKNU in the coastal waters. The change of position with time for the ship turning under the rudder angle of port <TEX>$30^{\circ}$</TEX> was correctly tracked with the turning circle of 940 m in diameter on the ENC of a PC-based ECDIS. Then, the dynamic information of the AIS system was updated every 6.29 seconds under the turning situation for the speed of 10.9 knots and every 21.65 seconds under the situation running at the speed of 11.05 knots on the straight line route of <TEX>$155^{\circ}$</TEX>, respectively. In case of AIS target tracking in the inshore zone behind large topographical obstructions, such as mountain and apartment buildings, the update rate of dynamic information was irregularly changed by the existence of land obstacles. However, the position tracking by AIS information under the situation existing no sea obstructions was achieved in real or near real-time and the instant presentation of course alternations for the ship was correctly monitored by using a PC-based ECDIS. From these results, we concluded that the PC-based ECDIS technology and methodology combined with the AIS information can be easily extended and applied to the surveillance and management for the fishing operation of fishing vessels in the coastal zone and in the EEZ fishing grounds.

A Partnership for Communication: A Personal Journey Through Amyotrophic Lateral Sclerosis

A Partnership for Communication: A Personal Journey Through Amyotrophic Lateral Sclerosis

An Overview on Primary Progressive Aphasia and Its Variants

We present a review of the literature on Primary Progressive Aphasia (PPA) together with the analysis of neuropschychological and neuroradiologic profiles of 42 PPA patients. Mesulam originally defined PPA as a progressive degenerative disorder characterized by isolated language impairment for at least two years. The most common variants of PPA are: (1) Progressive nonfluent aphasia (PNFA), (2) semantic dementia (SD), (3) logopenic progressive aphasia (LPA). PNFA is characterized by labored speech, agrammatism in production, and/or comprehension. In some cases the syndrome begins with isolated deficits in speech. SD patients typically present with loss of word and object meaning and surface dyslexia. LPA patients have word-finding difficulties, syntactically simple but accurate language output and impaired sentence comprehension. The neuropsychological data demonstrated that SD patients show the most characteristic pattern of impairment, while PNFA and LPA overlap within many cognitive domains. The neuroimaging analysis showed left perisylvian region involvement. A comprehensive cognitive, neuroimaging and pathological approach is necessary to identify the clinical and pathogenetic features of different PPA variants.

Method and apparatus for translating natural-language speech using multiple output phrases

A multi-lingual translation system that provides multiple output sentences for a given word or phrase. Each output sentence for a given word or phrase reflects, for example, a different emotional emphasis, dialect, accents, loudness or rates of speech. A given output sentence could be selected automatically, or manually as desired, to create a desired effect. For example, the same output sentence for a given word or phrase can be recorded three times, to selectively reflect excitement, sadness or fear. The multi-lingual translation system includes a phrase-spotting mechanism, a translation mechanism, a speech output mechanism and optionally, a language understanding mechanism or an event measuring mechanism or both. The phrase-spotting mechanism identifies a spoken phrase from a restricted domain of phrases. The language understanding mechanism, if present, maps the identified phrase onto a small set of formal phrases. The translation mechanism maps the formal phrase onto a well-formed phrase in one or more target languages. The speech output mechanism produces high-quality output speech. The speech output may be time synchronized to the spoken phrase using the output of the event measuring mechanism.

Text and speech translation by means of subsequential transducers

The full paper explores the possibility of using Subsequential Transducers (SST), a finite state model, in limited domain translation tasks, both for text and speech input. A distinctive advantage of SSTs is that they can be efficiently learned from sets of input-output examples by means of OSTIA, the Onward Subsequential Transducer Inference Algorithm (Oncina et al. 1993). In this work a technique is proposed to increase the performance of OSTIA by reducing the asynchrony between the input and output sentences, the use of error correcting parsing to increase the robustness of the models is explored, and an integrated architecture for speech input translation by means of SSTs is described.