Refine
Document Type
- Part of a Book (5)
- Conference Proceeding (4)
- Article (2)
Keywords
- Gesprochene Sprache (5)
- Korpus <Linguistik> (5)
- Deutsch (3)
- Sprecherwechsel (3)
- ASR (2)
- Annotation (2)
- Automatische Spracherkennung (2)
- Gestik (2)
- Konversationsanalyse (2)
- Plurizentrische Sprache (2)
Publicationstate
- Veröffentlichungsversion (7)
- Zweitveröffentlichung (3)
- Postprint (2)
Reviewstate
- Peer-Review (11) (remove)
Publisher
- European Language Resources Association (2)
- Association for Computational Linguistics (1)
- Association for Computational Linguistics ( ACL ); Curran Associates, Inc. (1)
- Elsevier (1)
- IEEE (1)
- John Benjamins (1)
- Paderborn University (1)
- Peter Lang (1)
- Stockholm University (1)
- University of Paderborn (1)
The newest generation of speech technology caused a huge increase of audio-visual data nowadays being enhanced with orthographic transcripts such as in automatic subtitling in online platforms. Research data centers and archives contain a range of new and historical data, which are currently only partially transcribed and therefore only partially accessible for systematic querying. Automatic Speech Recognition (ASR) is one option of making that data accessible. This paper tests the usability of a state-of-the-art ASR-System on a historical (from the 1960s), but regionally balanced corpus of spoken German, and a relatively new corpus (from 2012) recorded in a narrow area. We observed a regional bias of the ASR-System with higher recognition scores for the north of Germany vs. lower scores for the south. A detailed analysis of the narrow region data revealed – despite relatively high ASR-confidence – some specific word errors due to a lack of regional adaptation. These findings need to be considered in decisions on further data processing and the curation of corpora, e.g. correcting transcripts or transcribing from scratch. Such geography-dependent analyses can also have the potential for ASR-development to make targeted data selection for training/adaptation and to increase the sensitivity towards varieties of pluricentric languages.
The newest generation of speech technology caused a huge increase of audio-visual data nowadays being enhanced with orthographic transcripts such as in automatic subtitling in online platforms. Research data centers and archives contain a range of new and historical data, which are currently only partially transcribed and therefore only partially accessible for systematic querying. Automatic Speech Recognition (ASR) is one option of making that data accessible. This paper tests the usability of a state-of-the-art ASR-System on a historical (from the 1960s), but regionally balanced corpus of spoken German, and a relatively new corpus (from 2012) recorded in a narrow area. We observed a regional bias of the ASR-System with higher recognition scores for the north of Germany vs. lower scores for the south. A detailed analysis of the narrow region data revealed – despite relatively high ASR-confidence – some specific word errors due to a lack of regional adaptation. These findings need to be considered in decisions on further data processing and the curation of corpora, e.g. correcting transcripts or transcribing from scratch. Such geography-dependent analyses can also have the potential for ASR-development to make targeted data selection for training/adaptation and to increase the sensitivity towards varieties of pluricentric languages.
Feedback utterances are among the most frequent in dialogue. Feedback is also a crucial aspect of all linguistic theories that take social interaction involving language into account. However, determining communicative functions is a notoriously difficult task both for human interpreters and systems. It involves an interpretative process that integrates various sources of information. Existing work on communicative function classification comes from either dialogue act tagging where it is generally coarse grained concerning the feed- back phenomena or it is token-based and does not address the variety of forms that feed- back utterances can take. This paper introduces an annotation framework, the dataset and the related annotation campaign (involving 7 raters to annotate nearly 6000 utterances). We present its evaluation not merely in terms of inter-rater agreement but also in terms of usability of the resulting reference dataset both from a linguistic research perspective and from a more applicative viewpoint.
Precise multimodal studies require precise synchronisation between audio and video signals. However, raw audio and audio from video recordings can be out of sync for several reasons. In order to re-synchronise them, a dynamic programming (DP) approach is presented here. Traditionally, DP is performed on the rectangular distance matrix comparing each value in signal A with each value in signal B. Previous work limited the search space using for example the Sakoe Chiba Band (Sakoe and Chiba, 1978). However, the overall space of the distance matrix remains identical. Here, a tunnel matrix and its according DP-algorithm are presented. The matrix contains merely the computed distance of two signals to a pre-specified bandwidth and the computational cost is equally reduced. An example implementation demonstrates the functionality on artificial data and on data from real audio and video recordings.
Smooth turn-taking in conversation depends in part on speakers being able to communicate their intention to hold or cede the floor. Both prosodic and gestural cues have been shown to be used in this context. We investigate the interplay of pitch movements and hand gestures at locations at which speaker change becomes relevant, comparing their use in German and Swedish. We find that there are some shared functions of prosody and gesture with regard to turn-taking in the two languages, but that these shared functions appear to be mediated by the different phonological demands on pitch in the two languages.
A syntax-based scheme for the annotation and segmentation of German spoken language interactions
(2018)
Unlike corpora of written language where segmentation can mainly be derived from orthographic punctuation marks, the basis for segmenting spoken language corpora is not predetermined by the primary data, but rather has to be established by the corpus compilers. This impedes consistent querying and visualization of such data. Several ways of segmenting have been proposed,
some of which are based on syntax. In this study, we developed and evaluated annotation and segmentation guidelines in reference to the topological field model for German. We can show that these guidelines are used consistently across annotators. We also investigated the influence of various interactional settings with a rather simple measure, the word-count per segment and unit-type. We observed that the word count and the distribution of each unit type differ in varying interactional settings and that our developed segmentation and annotation guidelines are used consistently across annotators. In conclusion, our syntax-based segmentations reflect interactional properties that are intrinsic to the social interactions that participants are involved in. This can be used for further analysis of social interaction and opens the possibility for automatic segmentation of transcripts.
Looking at gestures as a means for communication, they can serve conversational participants at several levels. As co-speech gestures, they can add information to the verbally expressed content and they can serve to manage turn-taking. In order to look closer at the interplay between these resources in face-to face conversation, we annotated hand gestures, syntactic completion points and the related turn-organisation, and measured the timing of gesture strokes and their lexical/phrasal referent. In a case study on German, we observe the trend that speakers vary less in gesturelexis on- and offsets when keeping the turn after syntactic completions than at speaker changes, backchannel or other locations of a conversation. This indicates that timing properties of non-verbal cues interact with verbal cues to manage turn-taking.
To date, little is known about prosodic accommodation and its conversational functions in instances of overlapping talk in conversation. A major conversational action that happens in overlap is turn competition. It is not known whether participants accommodate prosodic parameters locally in the overlapped turn (initialisation) or access a repertoire of prosodic patterns that refer to general prosodic parameter norms (normalisation) when competing for the turn in overlap. This paper investigates the initialisation and normalisation of fundamental frequency (f0) and assesses its role as a resource for turn competition in overlap. We drew instances of overlapping talk from a corpus of conversational multi-party interactions in British English. We annotated the overlaps on a competitiveness scale and categorised them by overlap onset position and conversational function. We automatically extracted f0 parameters from the speech signal and processed them into f0 accommodation features that represent the normalising or the initialising use of f0. Using decision tree classification we found that f0 accommodation is only relevant as a turn competitive resource in overlaps that start clearly before a speaker transition. In this turn context, we found that normalising and initialising f0 features can both be relevant turn competitive resources. Their deployment depends on the conversational function of overlap.
For many reasons, Mennonite Low German is a language whose documentation and investigation is of great importance for linguistics. To date, most research projects that deal with this language and/ or its speakers have had a relatively narrow focus, with many of the data cited being of limited relevance beyond the projects for which they were collected. In order to create a resource for a broad range of researchers, especially those working on Mennonite Low German, the dataset presented here has been transformed into a structured and searchable corpus that is accessible online. The translations of 46 English, Spanish, or Portuguese stimulus sentences into Mennonite Low German by 321 consultants form the core of the MEND-corpus (Mennonite Low German in North and South America) in the Archive for Spoken German. In addition to describing the origin of this corpus and discussing possibilities and limitations for further research, we discuss the technical structure and search possibilities of the Database for Spoken German. Among other things, this database allows for a structured search of metadata, a context-sensitive token search, and the generation of virtual corpora that can be shared with others. Moreover, thanks to its text-sound alignment, one can easily switch from a particular text section of the corpus to the corresponding audio section. Aside from the desire to equip the reader with the technical knowledge necessary to use this corpus, a further goal of this paper is to demonstrate that the corpus still offers many possibilities for future research.
This paper examines multi-unit turns that allow speakers to retrospectively close the prior sequence while prospectively launching a new sequence, which Schegloff (1986) referred to as interlocking organization. Using English telephone conversations as data, we focus on how multi-unit turns are used for topic shifts, and show that interlocking organization operates in conjunction with other phonetic and lexical features, such as increased pitch and overt markers of disjunction (e.g., “listen”). In addition, speakers utilize an audible inbreath that is placed between the first and the second units as a central interactional resource to project further talk, thereby suppressing speaker transition and possibly highlighting the action delivered in the second unit as being distinctly new. We propose that interlocking multi-unit turns, when used to make topically disjunctive moves, promote progressivity by avoiding a possible lapse in turn transition