Multilingual processing of speech via web services

Kisler, Thomas; Reichel, Uwe D.; Schiel, Florian

doi:10.1016/j.csl.2017.01.005

Cited by 302 publications

(197 citation statements)

References 8 publications

Supporting

Mentioning

168

Contrasting

Unclassified

Order By: Relevance

“…Recordings were orthographically transcribed by a native speaker of Yucatecan Spanish. They were then automatically aligned using BAS Pipeline online service (v. 2.22;Kisler et al 2017). Later, they were manually corrected by two labelers in Praat (v. 6.0.43;Boersma and Weenink 2009) under the supervision of the first author, who also conducted final corrections on the labels to ensure accuracy and coherence in the measurement.…”

Section: Discussionmentioning

confidence: 99%

Lack of Syllable Duration as a Post-Lexical Acoustic Cue in Spanish in Contact with Maya

García

Uth

2019

Languages

View full text Add to dashboard Cite

This paper focuses on the duration of stressed syllables in broad versus contrastive focus in Yucatecan Spanish and examines its connection with Spanish–Maya bilingualism. We examine the claim that phonemic vowel length in one language prevents the use of syllable duration as a post-lexical acoustic cue in another. We study the duration of stressed syllables of nouns in subject and object position in subject-verb-object (SVO) sentences (broad and contrastive focus) of a semi-spontaneous production task. One thousand one hundred and twenty-six target syllables of 34 mono- and bilingual speakers were measured and submitted to linear mixed-effects models. Although the target syllables were slightly longer in contrastive focus, duration was not significant, nor was the effect of bilingualism. The results point to duration not constituting a cue to focus marking in Yucatecan Spanish. Finally, it is discussed how this result relates to the strong influence of Yucatec Maya on Yucatecan Spanish prosody observed by both scholars and native speakers of Yucatecan Spanish and other Mexican varieties of Spanish.

show abstract

Section: Discussionmentioning

confidence: 99%

Lack of Syllable Duration as a Post-Lexical Acoustic Cue in Spanish in Contact with Maya

García

Uth

2019

Languages

View full text Add to dashboard Cite

show abstract

“…Evanini et al, 2009 andRosenfelder et al, 2014 on the FAVE automated vowel extraction program and Reddy and Stanford, 2015 on DARLA, which automatically generates transcriptions with ASR and extracts vowels using FAVE). Figure 5 shows the output of a FA test using the BASWebServices of the Ludwig Maximilian University of Munich (Schiel, 1999;Kisler et al, 2017). 25 Their WebMAUSmodule segments an audio file into SAMPA phonetic segments given an orthographic transcription.…”

Section: Forced Alignment For Automatic Segmentation and Phonetic Tramentioning

confidence: 99%

Clearing the Transcription Hurdle in Dialect Corpus Building: The Corpus of Southern Dutch Dialects as Case Study

Ghyselen¹,

Breitbarth²,

Farasyn³

et al. 2020

Front. Artif. Intell.

View full text Add to dashboard Cite

This paper discusses how the transcription hurdle in dialect corpus building can be cleared. While corpus analysis has strongly gained in popularity in linguistic research, dialect corpora are still relatively scarce. This scarcity can be attributed to several factors, one of which is the challenging nature of transcribing dialects, given a lack of both orthographic norms for many dialects and speech technological tools trained on dialect data. This paper addresses the questions (i) how dialects can be transcribed efficiently and (ii) whether speech technological tools can lighten the transcription work. These questions are tackled using the Southern Dutch dialects (SDDs) as case study, for which the usefulness of automatic speech recognition (ASR), respeaking, and forced alignment is considered. Tests with these tools indicate that dialects still constitute a major speech technological challenge. In the case of the SDDs, the decision was made to use speech technology only for the word-level segmentation of the audio files, as the transcription itself could not be sped up by ASR tools. The discussion does however indicate that the usefulness of ASR and other related tools for a dialect corpus project is strongly determined by the sound quality of the dialect recordings, the availability of statistical dialect-specific models, the degree of linguistic differentiation between the dialects and the standard language, and the goals the transcripts have to serve.

show abstract

“…IPA Transcription Nasals /n/, /m/, /N/ Sibilants /s/, /S/, /z/, /Z/ Fricatives /f/, /v/, /j/, /C/, /h/ Voiced stops /b/, /d/, /g/ Voiceless stops /p/, /t/, /k/ recordings, the BAS CLARIN web service is used [5]. This web service provides a forced alignment tool based on the Munich Automatic Segmentation system presented in [15].…”

Section: Groupmentioning

confidence: 99%

Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users

Arias-Vergara

Orozco-Arroyave

Gollwitzer

et al. 2019

Text, Speech, and Dialogue

View full text Add to dashboard Cite

People with postlingual onset of deafness often present speech production problems even after hearing rehabilitation by cochlear implantation. In this paper, the speech of 20 postlingual (aged between 33 and 78 years old) and 20 healthy control (aged between 31 and 62 years old) German native speakers is analyzed considering acoustic features extracted from Consonant-to-Vowel (CV) and Vowel-to-Consonant (VC) transitions. The transitions are analyzed with reference to the manner of articulation of consonants according to 5 groups: nasals, sibilants, fricatives, voiced stops, and voiceless stops. Automatic classification between cochlear implant (CI) users and healthy speakers shows accuracies of up to 93%. Considering CV transitions, it is possible to detect specific features of altered speech of CI users. More features are to be evaluated in the future. A comprehensive evaluation of speech changes of CI users will help in the rehabilitation after deafening.

show abstract

Multilingual processing of speech via web services

Cited by 302 publications

References 8 publications

Lack of Syllable Duration as a Post-Lexical Acoustic Cue in Spanish in Contact with Maya

Lack of Syllable Duration as a Post-Lexical Acoustic Cue in Spanish in Contact with Maya

Clearing the Transcription Hurdle in Dialect Corpus Building: The Corpus of Southern Dutch Dialects as Case Study

Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users

Contact Info

Product

Resources

About