Automatic detection and segmentation of pronunciation variants in German speech corpora

Kipp, Andreas; Wesenick, Maria-Barbara; Schiel, Florian

doi:10.1109/icslp.1996.607048

Cited by 30 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schuppler and colleagues (2011) automatically transcribed part of the spontaneous speech incorporated in the IFA corpus (van Son, Binnenpoorte, van den Heuvel, & Pols, 2001) and found that 14% of the segments were transcribed differently in their transcriptions than in the transcriptions created with a different automatic method and corrected by human transcribers. Since disagreements between human transcribers may vary between 5.6% and 58%, depending on the degree of spontaneity of the speech (Kipp, Wesenick, & Schiel, 1996, 1997Ernestus & Baayen, 2011), these results strongly suggest that the transcriptions automatically generated with their transcriber and procedure are as reliable as human made transcriptions.…”

Section: Methodsmentioning

confidence: 62%

The effect of speech situation on the occurrence of reduced word pronunciation variants

Ernestus

Hanique

Verboom

2015

Journal of Phonetics

View full text Add to dashboard Cite

This article presents two studies investigating how the situation in which speech is uttered affects the frequency with which words are reduced. Study 1 is based on the Spoken Dutch Corpus, which consists of 15 components, nearly all representing a different speech situation. This study shows that the components differ in how often ten semantically weak words are highly reduced. The differences are especially large between the components with scripted and unscripted speech. Within the component group of unscripted speech, the formality of the situation shows an effect. Study 2 investigated segment reduction in a shadowing experiment in which participants repeated Dutch carefully and casually articulated sentences. Prefixal schwa and suffixal /t/ were absent in participants' responses to both sentences types as often as in formal interviews. If a segment was absent, this appeared to be mostly due to extreme coarticulation, unlike in speech produced in less formal situations. Speakers thus adapted more to the formal situation of the experiment than to the stimuli to be shadowed. We conclude that speech situation affects the occurrence of reduced word pronunciation variants, which should be accounted for by psycholinguistic models of speech production and comprehension.

show abstract

Section: Methodsmentioning

confidence: 62%

The effect of speech situation on the occurrence of reduced word pronunciation variants

Ernestus

Hanique

Verboom

2015

Journal of Phonetics

View full text Add to dashboard Cite

show abstract

“…Overall, we observed a 14.0% discrepancy. A comparison of that percentage with values found in the literature shows that our transcription is as reliable as a human transcription: Disagreements between human transcribers may vary between 5.6% and 21.2%, depending on the degree of spontaneity of the speech (Kipp et al, 1997(Kipp et al, , 1996. Moreover, the discrepancy is small compared to other discrepancies between human-made and automatically generated transcriptions reported in the literature.…”

Section: Validation Of the Phonemic Transcription 341 Materials And mentioning

confidence: 57%

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

Schuppler

Ernestus

Scharenborg

et al. 2011

Journal of Phonetics

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

“…This difficulty is also reflected in the inter-human labeling disagreement of phonetic transcriptions (5.6% for read speech vs. 21.2% for conversational speech; Kipp et al 1996Kipp et al , 1997. Hence, it is not surprising that our classification performance is overall worse for conversational speech than for read speech.…”

Section: Discussionmentioning

confidence: 99%

“…Schuppler et al 2014), the number of incorrect labels in training and test data is higher. For this same reason, the creation of broad phonetic transcriptions is a much more difficult task for conversational speech than for read speech, which is for instance also reflected by substantially higher inter-labeler disagreement [5.6% for read speech vs. 21.2% for conversational speech (Kipp et al 1996(Kipp et al , 1997]. …”

Section: Impact Of Inaccurate Labelingmentioning

confidence: 99%

Rethinking classification results based on read speech, or: why improvements do not always transfer to other speaking styles

Schuppler

2017

Int J Speech Technol

View full text Add to dashboard Cite

show abstract

Automatic detection and segmentation of pronunciation variants in German speech corpora

Cited by 30 publications

References 4 publications

The effect of speech situation on the occurrence of reduced word pronunciation variants

The effect of speech situation on the occurrence of reduced word pronunciation variants

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

Rethinking classification results based on read speech, or: why improvements do not always transfer to other speaking styles

Contact Info

Product

Resources

About