Constitution d’un Corpus de Français Langue Etrangère destiné aux Apprenants Allemands

Fauth, Camille; Bonneau, Anne; Mella, Odile; Colotte, Vincent; Fohr, Dominique; Jouvet, Denis; Laprie, Yves; Trouvain, Jürgen

doi:10.1051/shsconf/20140801186

Cited by 3 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The learner speech data used in this work has been excerpted from the IFCASL corpus [13], a collection of phonetically diverse utterances in French and German spoken by both native speakers and non-native speakers with the other language as L1. The corpus contains recordings of approximately 50 L1 speakers of each language reading sentences (and a short text) in both languages, such that both L1 and L2 speech was recorded for each speaker.…”

Section: The Ifcasl Corpus Of Learner Speechmentioning

confidence: 99%

“…Only utterances from the sub-corpus of L2 German speech by L1 French speakers (henceforth IFCASL-FG) were manually annotated; native utterances from the L1 German sub-corpus (IFCASL-GG) were assumed to contain only correct lexical stress realizations. In addition to the recordings themselves, the IFCASL corpus contains phone-and word-level segmentations of each utterance, produced automatically by forced alignment [13]. Although the corpus also contains manual corrections of these segmentations, the work reported here relies exclusively on the automatic segmentations to mimic the conditions of a fully automatic CAPT system.…”

Section: The Ifcasl Corpus Of Learner Speechmentioning

confidence: 99%

See 1 more Smart Citation

Automatic classification of lexical stress errors for German CAPT

Vakil,

Trouvain

2015

Speech and Language Technology in Education (SLaTE 2015)

View full text Add to dashboard Cite

Lexical stress plays an important role in the prosody of German, and presents a considerable challenge to native speakers of languages such as French who are learning German as a foreign language. These learners stand to benefit greatly from Computer-Assisted Pronunciation Training (CAPT) systems which can offer individualized corrective feedback on such errors, and reliable automatic detection of these errors is a prerequisite for developing such systems. With this motivation, this paper presents an exploration of the use of machine learning methods to classify non-native German lexical stress errors. In classification experiments using a manually-annotated corpus of German word utterances by native French speakers, the highest observed agreement between the classifier's output and the gold-standard labels exceeded the inter-annotator agreement between humans asked to classify lexical stress errors in the same data. These results establish the viability of classification-based diagnosis of lexical stress errors for German CAPT.

show abstract

Section: The Ifcasl Corpus Of Learner Speechmentioning

confidence: 99%

Section: The Ifcasl Corpus Of Learner Speechmentioning

confidence: 99%

Automatic classification of lexical stress errors for German CAPT

Vakil,

Trouvain

2015

Speech and Language Technology in Education (SLaTE 2015)

View full text Add to dashboard Cite

show abstract

“…Within the framework of the IFCASL 1 project [2], a large speech corpus of native and non-native speech for the French-German language pair was designed. This corpus is intended to developing and validating: (i) diagnosis and feedback 1 Individualised Feedback in Computer-Assisted Spoken Language learning (IFCASL), supported by ANR (Agence Nationale de la Recherche and DFG (Deutsche Forschungsgemeinschaft) algorithms, (ii) automatic phonetic alignment systems.…”

Section: Introductionmentioning

confidence: 99%

Inter-annotator agreement for a speech corpus pronounced by French and German language learners

Mella,

Fohr,

Bonneau

2015

Speech and Language Technology in Education (SLaTE 2015)

View full text Add to dashboard Cite

This paper presents the results of an investigation of interannotator agreement for the non-native and native French part of the IFCASL corpus. This large bilingual speech corpus for French and German language learners was manually annotated by several annotators. This manual annotation is the starting point which will be used both to improve the automatic segmentation algorithms and derive diagnosis and feedback. The agreement is evaluated by comparing the manual alignments of seven annotators to the manual alignment of an expert, for 18 sentences. Whereas results for the presence of the devoicing diacritic show a certain degree of disagreement between the annotators and the expert, there is a very good consistency between annotators and the expert for temporal boundaries as well as insertions and deletions. We find a good overall agreement for boundaries between annotators and expert with a mean deviation of 7.6 ms and 93% of boundaries within 20 ms.

show abstract

“…The speech corpus was designed, using a two-step process [10], to focus on some phenomena of interest for the French/German language pair, covering segmental and prosodic levels as well as spelling problems. A non-exhaustive list of selected difficulties can be found in Table 1 (note that SAMPA notation [11] is used throughout this paper).…”

Section: Introductionmentioning

confidence: 99%

“…The subjects were seated in a quiet room and read the sentences from the screen of a Windows laptop (or repeated them, depending on the speaking condition), with a headset microphone (AKG C520) connected to an Audiobox (M Audio Fast track). For details see [10].…”

Section: Introductionmentioning

confidence: 99%

Analysis of phone confusion matrices in a manually annotated French-German learner corpus

Jouvet,

Bonneau,

Trouvain

et al. 2015

Speech and Language Technology in Education (SLaTE 2015)

View full text Add to dashboard Cite

This paper presents an analysis of the non-native and native pronunciations observed in a phonetically annotated bilingual French-German corpus. After a forced-choice automatic annotation a large part of the corpus was checked and corrected manually on the phone level which allows a detailed comparison of the realized sounds with the expected sounds. The analysis is reported in terms of phone confusion matrices for selected error-prone classes of sounds. It revealed that German learners of French have most problems with obstruents in word-final position whereas French learners of German show complex interferences with the vowel contrasts for length and quality. Finally, the correct pronunciation rate of the sounds, for several phonetic classes, is analyzed with respect to the learner's level, and compared to native pronunciations. One outcome is that different sound classes show different correct rates over the proficiency levels. For the German data the frequently occurring syllabic [=n] is a prime indicator of the proficiency level.

show abstract

Constitution d’un Corpus de Français Langue Etrangère destiné aux Apprenants Allemands

Cited by 3 publications

References 28 publications

Automatic classification of lexical stress errors for German CAPT

Automatic classification of lexical stress errors for German CAPT

Inter-annotator agreement for a speech corpus pronounced by French and German language learners

Analysis of phone confusion matrices in a manually annotated French-German learner corpus

Contact Info

Product

Resources

About