Publications

Displaying 1 - 7 of 7
  • Bögels, S., Casillas, M., & Levinson, S. C. (2018). Planning versus comprehension in turn-taking: Fast responders show reduced anticipatory processing of the question. Neuropsychologia, 109, 295-310. doi:10.1016/j.neuropsychologia.2017.12.028.

    Abstract

    Rapid response latencies in conversation suggest that responders start planning before the ongoing turn is finished. Indeed, an earlier EEG study suggests that listeners start planning their responses to questions as soon as they can (Bögels, S., Magyari, L., & Levinson, S. C. (2015). Neural signatures of response planning occur midway through an incoming question in conversation. Scientific Reports, 5, 12881). The present study aimed to (1) replicate this early planning effect and (2) investigate whether such early response planning incurs a cost on participants’ concurrent comprehension of the ongoing turn. During the experiment participants answered questions from a confederate partner. To address aim (1), the questions were designed such that response planning could start either early or late in the turn. Our results largely replicate Bögels et al. (2015) showing a large positive ERP effect and an oscillatory alpha/beta reduction right after participants could have first started planning their verbal response, again suggesting an early start of response planning. To address aim (2), the confederate's questions also contained either an expected word or an unexpected one to elicit a differential N400 effect, either before or after the start of response planning. We hypothesized an attenuated N400 effect after response planning had started. In contrast, the N400 effects before and after planning did not differ. There was, however, a positive correlation between participants' response time and their N400 effect size after planning had started; quick responders showed a smaller N400 effect, suggesting reduced attention to comprehension and possibly reduced anticipatory processing. We conclude that early response planning can indeed impact comprehension processing.

    Additional information

    mmc1.pdf
  • Cristia, A., Ganesh, S., Casillas, M., & Ganapathy, S. (2018). Talker diarization in the wild: The case of child-centered daylong audio-recordings. In Proceedings of Interspeech 2018 (pp. 2583-2587). doi:10.21437/Interspeech.2018-2078.

    Abstract

    Speaker diarization (answering 'who spoke when') is a widely researched subject within speech technology. Numerous experiments have been run on datasets built from broadcast news, meeting data, and call centers—the task sometimes appears close to being solved. Much less work has begun to tackle the hardest diarization task of all: spontaneous conversations in real-world settings. Such diarization would be particularly useful for studies of language acquisition, where researchers investigate the speech children produce and hear in their daily lives. In this paper, we study audio gathered with a recorder worn by small children as they went about their normal days. As a result, each child was exposed to different acoustic environments with a multitude of background noises and a varying number of adults and peers. The inconsistency of speech and noise within and across samples poses a challenging task for speaker diarization systems, which we tackled via retraining and data augmentation techniques. We further studied sources of structured variation across raw audio files, including the impact of speaker type distribution, proportion of speech from children, and child age on diarization performance. We discuss the extent to which these findings might generalize to other samples of speech in the wild.
  • Räsänen, O., Seshadri, S., & Casillas, M. (2018). Comparison of syllabification algorithms and training strategies for robust word count estimation across different languages and recording conditions. In Proceedings of Interspeech 2018 (pp. 1200-1204). doi:10.21437/Interspeech.2018-1047.

    Abstract

    Word count estimation (WCE) from audio recordings has a number of applications, including quantifying the amount of speech that language-learning infants hear in their natural environments, as captured by daylong recordings made with devices worn by infants. To be applicable in a wide range of scenarios and also low-resource domains, WCE tools should be extremely robust against varying signal conditions and require minimal access to labeled training data in the target domain. For this purpose, earlier work has used automatic syllabification of speech, followed by a least-squares-mapping of syllables to word counts. This paper compares a number of previously proposed syllabifiers in the WCE task, including a supervised bi-directional long short-term memory (BLSTM) network that is trained on a language for which high quality syllable annotations are available (a “high resource language”), and reports how the alternative methods compare on different languages and signal conditions. We also explore additive noise and varying-channel data augmentation strategies for BLSTM training, and show how they improve performance in both matching and mismatching languages. Intriguingly, we also find that even though the BLSTM works on languages beyond its training data, the unsupervised algorithms can still outperform it in challenging signal conditions on novel languages.
  • Casillas, M., Bergelson, E., Warlaumont, A. S., Cristia, A., Soderstrom, M., VanDam, M., & Sloetjes, H. (2017). A New Workflow for Semi-automatized Annotations: Tests with Long-Form Naturalistic Recordings of Childrens Language Environments. In Proceedings of Interspeech 2017 (pp. 2098-2102). doi:10.21437/Interspeech.2017-1418.

    Abstract

    Interoperable annotation formats are fundamental to the utility, expansion, and sustainability of collective data repositories.In language development research, shared annotation schemes have been critical to facilitating the transition from raw acoustic data to searchable, structured corpora. Current schemes typically require comprehensive and manual annotation of utterance boundaries and orthographic speech content, with an additional, optional range of tags of interest. These schemes have been enormously successful for datasets on the scale of dozens of recording hours but are untenable for long-format recording corpora, which routinely contain hundreds to thousands of audio hours. Long-format corpora would benefit greatly from (semi-)automated analyses, both on the earliest steps of annotation—voice activity detection, utterance segmentation, and speaker diarization—as well as later steps—e.g., classification-based codes such as child-vs-adult-directed speech, and speech recognition to produce phonetic/orthographic representations. We present an annotation workflow specifically designed for long-format corpora which can be tailored by individual researchers and which interfaces with the current dominant scheme for short-format recordings. The workflow allows semi-automated annotation and analyses at higher linguistic levels. We give one example of how the workflow has been successfully implemented in a large cross-database project.
  • Casillas, M., & Frank, M. C. (2017). The development of children's ability to track and predict turn structure in conversation. Journal of Memory and Language, 92, 234-253. doi:10.1016/j.jml.2016.06.013.

    Abstract

    Children begin developing turn-taking skills in infancy but take several years to fluidly integrate their growing knowledge of language into their turn-taking behavior. In two eye-tracking experiments, we measured children’s anticipatory gaze to upcoming responders while controlling linguistic cues to turn structure. In Experiment 1, we showed English and non-English conversations to English-speaking adults and children. In Experiment 2, we phonetically controlled lexicosyntactic and prosodic cues in English-only speech. Children spontaneously made anticipatory gaze switches by age two and continued improving through age six. In both experiments, children and adults made more anticipatory switches after hearing questions. Consistent with prior findings on adult turn prediction, prosodic information alone did not increase children’s anticipatory gaze shifts. But, unlike prior work with adults, lexical information alone was not sucient either—children’s performance was best overall with lexicosyntax and prosody together. Our findings support an account in which turn tracking and turn prediction emerge in infancy and then gradually become integrated with children’s online linguistic processing.
  • Casillas, M., Amatuni, A., Seidl, A., Soderstrom, M., Warlaumont, A., & Bergelson, E. (2017). What do Babies hear? Analyses of Child- and Adult-Directed Speech. In Proceedings of Interspeech 2017 (pp. 2093-2097). doi:10.21437/Interspeech.2017-1409.

    Abstract

    Child-directed speech is argued to facilitate language development, and is found cross-linguistically and cross-culturally to varying degrees. However, previous research has generally focused on short samples of child-caregiver interaction, often in the lab or with experimenters present. We test the generalizability of this phenomenon with an initial descriptive analysis of the speech heard by young children in a large, unique collection of naturalistic, daylong home recordings. Trained annotators coded automatically-detected adult speech 'utterances' from 61 homes across 4 North American cities, gathered from children (age 2-24 months) wearing audio recorders during a typical day. Coders marked the speaker gender (male/female) and intended addressee (child/adult), yielding 10,886 addressee and gender tags from 2,523 minutes of audio (cf. HB-CHAAC Interspeech ComParE challenge; Schuller et al., in press). Automated speaker-diarization (LENA) incorrectly gender-tagged 30% of male adult utterances, compared to manually-coded consensus. Furthermore, we find effects of SES and gender on child-directed and overall speech, increasing child-directed speech with child age, and interactions of speaker gender, child gender, and child age: female caretakers increased their child-directed speech more with age than male caretakers did, but only for male infants. Implications for language acquisition and existing classification algorithms are discussed.
  • Schuller, B., Steidl, S., Batliner, A., Bergelson, E., Krajewski, J., Janott, C., Amatuni, A., Casillas, M., Seidl, A., Soderstrom, M., Warlaumont, A. S., Hidalgo, G., Schnieder, S., Heiser, C., Hohenhorst, W., Herzog, M., Schmitt, M., Qian, K., Zhang, Y., Trigeorgis, G. and 2 moreSchuller, B., Steidl, S., Batliner, A., Bergelson, E., Krajewski, J., Janott, C., Amatuni, A., Casillas, M., Seidl, A., Soderstrom, M., Warlaumont, A. S., Hidalgo, G., Schnieder, S., Heiser, C., Hohenhorst, W., Herzog, M., Schmitt, M., Qian, K., Zhang, Y., Trigeorgis, G., Tzirakis, P., & Zafeiriou, S. (2017). The INTERSPEECH 2017 computational paralinguistics challenge: Addressee, cold & snoring. In Proceedings of Interspeech 2017 (pp. 3442-3446). doi:10.21437/Interspeech.2017-43.

    Abstract

    The INTERSPEECH 2017 Computational Paralinguistics Challenge addresses three different problems for the first time in research competition under well-defined conditions: In the Addressee sub-challenge, it has to be determined whether speech produced by an adult is directed towards another adult or towards a child; in the Cold sub-challenge, speech under cold has to be told apart from ‘healthy’ speech; and in the Snoring subchallenge, four different types of snoring have to be classified. In this paper, we describe these sub-challenges, their conditions, and the baseline feature extraction and classifiers, which include data-learnt feature representations by end-to-end learning with convolutional and recurrent neural networks, and bag-of-audiowords for the first time in the challenge series

Share this page