A spoken dialog system for the Dutch public transport information service

Strik, Helmer; Russel, Albert; Heuvel, H. van den; Cucchiarini, Catia; Boves, L.W.J.

doi:10.1007/bf02208824

Cited by 48 publications

(50 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies on [n]-deletion in Dutch have reported that [n] was absent in approximately 40% of the word tokens (Wester et al, 1998;Kessens et al, 2000). An explanation of this latter much lower frequency is that these studies were based on a corpus of careful speech (Strik et al, 1997). Another explanation could be differences in the regional background of the speakers.…”

Section: Results Andmentioning

confidence: 92%

“…reported similar frequencies for [r] deletion after schwa in Dutch (56%) as we found. Their study was based on a corpus of spontaneous human-machine interactions Strik et al (1997). Lower deletion rates have been reported for careful speech: 29% deletion for tokens where [r] preceded a consonant and followed schwa, long vowels or unstressed short vowels (Wester et al, 1998).…”

Section: Absence Of [R]mentioning

confidence: 99%

See 1 more Smart Citation

Acoustic reduction in conversational Dutch: A quantitative analysis based on automatically generated segmental transcriptions

Schuppler

Ernestus

Scharenborg

et al. 2011

Journal of Phonetics

Self Cite

View full text Add to dashboard Cite

In spontaneous, conversational speech, words are often reduced compared to their citation forms, such that a word like yesterday may sound like ['jESeI]. The present paper investigates such acoustic reduction . The study of reduction needs large corpora that are transcribed phonetically. The first part of this paper describes an automatic transcription procedure used to obtain such a large phonetically transcribed corpus of Dutch spontaneous dialogues, which is subsequently used for the investigation of acoustic reduction. First, the orthographic transcription were adapted for automatic processing. Next, the phonetic transcription of the corpus was created by means of a forced alignment with a lexicon with multiple pronunciation variants per word. These variants were generated by applying phonological and reduction rules to the canonical phonetic transcriptions of the words. The second part of this paper reports the results of a quantitative analysis of reduction in the corpus on the basis of the generated transcriptions and gives an inventory of segmental reductions in standard Dutch. Overall, we found that reduction is more pervasive in spontaneous Dutch than previously documented.

show abstract

Section: Results Andmentioning

confidence: 92%

Section: Absence Of [R]mentioning

confidence: 99%

Acoustic reduction in conversational Dutch: A quantitative analysis based on automatically generated segmental transcriptions

Schuppler

Ernestus

Scharenborg

et al. 2011

Journal of Phonetics

Self Cite

View full text Add to dashboard Cite

show abstract

“…To calculate the quantitative measures, the continuous speech recognizer (CSR) described in Strik et al (1997) was used. Feature extraction is done every 10 ms for frames with a width of 16 ms.…”

Section: The Autom Atic Speech Recognizermentioning

confidence: 99%

Quantitative assessment of second language learners’ fluency by means of automatic speech recognition technology

Cucchiarini

Strik

Boves

2000

The Journal of the Acoustical Society of America

Self Cite

188

156

View full text Add to dashboard Cite

To determine whether expert fluency ratings of read speech can be predicted on the basis of automatically calculated temporal measures of speech quality, an experiment was conducted with read speech of 20 native and 60 non-native speakers of Dutch. The speech material was scored for fluency by nine experts and was then analyzed by means of an automatic speech recognizer in terms of quantitative measures such as speech rate, articulation rate, number and length of pauses, number of dysfluencies, mean length of runs, and phonation/time ratio. The results show that expert ratings of fluency in read speech are reliable (Cronbach's a varies between 0.90 and 0.96) and that these ratings can be predicted on the basis of quantitative measures: for six automatic measures the magnitude of the correlations with the fluency scores varies between 0.81 and 0.93. Rate of speech appears to be the best predictor: correlations vary between 0.90 and 0.93. Two other important determinants of reading fluency are the rate at which speakers articulate the sounds and the number of pauses they make. Apparently, rate of speech is such a good predictor of perceived fluency because it incorporates these two aspects.

show abstract

“…Various home automation system for safety are created using ZigBee wireless communication module along with microcontroller [11] . There is an existence of a Spoken Dialog interface in Dutch for Public Transport Information Service to get the information about journeys between two train stations [12].…”

Section: Related Workmentioning

confidence: 99%

Marathi Speech Interface System for the Activation and Controlling of Electronic Equipment

Gaikwad¹

2015

IJRITCC

View full text Add to dashboard Cite

Abstract-This paper provides a framework to design Marathi speech recognition interface system to control the electronic equipment like fan and electric bulb. This system is designed using HM2007 speech recognition kit. HM2007 is a single chip CMOS LSI circuit with on chip front end and analysis. The interface system is trained with the database of total 15 most commonly used words to activate and control the equipment. The training and testing of Marathi speech interface system is done in noisy and noise free environment. The performance of MSAEE system calculated on the basis of False Acceptance Rate (FAR), False Recognition Rate (FRR), Word Error Rate (WER), sensitivity, specificity and FMeasure. The average accuracy obtained in noisy environment is 88.77% whereas the accuracy of 98.88% is achieved without noise. The sensitivity value is superior then specificity means MSAEE system is robust and dynamic. FAR values is most significant than value of FRR so, it means MSAEE system proved a best solution for controlling electrical appliances. HM2007 is found to be most promising speech recognition IC, through which many speech interface application can be built that will be beneficial to people with less mobility.

show abstract

A spoken dialog system for the Dutch public transport information service

Cited by 48 publications

References 12 publications

Acoustic reduction in conversational Dutch: A quantitative analysis based on automatically generated segmental transcriptions

Acoustic reduction in conversational Dutch: A quantitative analysis based on automatically generated segmental transcriptions

Quantitative assessment of second language learners’ fluency by means of automatic speech recognition technology

Marathi Speech Interface System for the Activation and Controlling of Electronic Equipment

Contact Info

Product

Resources

About