Skip to main content

Advertisement

SpringerLink
Log in

Alcohol language corpus: the first public corpus of alcoholized German speech

  • Original Paper
  • Published:
Language Resources and Evaluation Aims and scope Submit manuscript

Abstract

The Alcohol Language Corpus (ALC) is the first publicly available speech corpus comprising intoxicated and sober speech of 162 female and male German speakers. Recordings are done in the automotive environment to allow for the development of automatic alcohol detection and to ensure a consistent acoustic environment for the alcoholized and the sober recording. The recorded speech covers a variety of contents and speech styles. Breath and blood alcohol concentration measurements are provided for all speakers. A transcription according to SpeechDat/Verbmobil standards and disfluency tagging as well as an automatic phonetic segmentation are part of the corpus. An Emu version of ALC allows easy access to basic speech parameters as well as the us of R for statistical analysis of selected parts of ALC. ALC is available without restriction for scientific or commercial use at the Bavarian Archive for Speech Signals.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Notes

  1. BAS is located at the Ludwig-Maximilians-Universität, München, Germany, http://www.bas.uni-muenchen.de/Bas.

  2. ‘Union against alcohol and drugs in traffic’ (Bund gegen Alkohol und Drogen im Strassenverkehr. URL http://www.bads.de/Alkohol/statistik.htm. Cited 2009).

  3. According to German law (2010) a BAC level of above 0.0005 is regarded as illegal in traffic.

  4. The number 60 roughly represents the degrees of freedom where the F statistic gets flattened; that is to say, the F-value does not change very much for degrees of freedom above 60, and therefore testing for significance does not improve much more above that number (Leisch 2009).

  5. A full listing of all screen prompts can be downloaded from http://www.bas.uni-muenchen.de/Bas/BasALCPROMPTS.

  6. Opel (GM) Astra gasoline (C1), VW Passat diesel (C2).

  7. Due to budget constraints this was done only for a subset of ALC we consider to be worth investigating with respect to irregularities: tongue twister, picture description, question answering, dialogue, read control and command (set A: 14 items, set N: 29 items).

  8. Including word fragments, dialectal variants and mispronunciations.

  9. For a detailed and up-to-date documentation on the BPF see http://www.bas.uni-muenchen.de/Bas/BasFormatseng.html.

  10. All phonetic symbols coded in SAM-PA (Wells 1997).

  11. See the BAS catalog at http://www.bas.uni-muenchen.de/Bas/BasALCeng.html for details; BAS and ELRA distribution fees apply.

  12. Paired t-test based on the averaged words per recording item per speaker.

  13. The percentages in Table 8 are given with regard to the number of word tokens in the respective sub-corpus; therefore the values are comparable across groups and genders.

References

  • Barfüsser, S., & Schiel, F. (2010). Disfluencies in alcoholized speech. IAFPA annual conference 2010, Trier, Germany.

  • Baumeister, B., & Schiel, F. (2010). On the effect of alcoholisation on fundamental frequency. IAFPA annual conference 2010, Trier, Germany.

  • Behne, D. M., Rivera, S. M., & Pisoni, D. B. (1991). Effects of alcohol on speech: Durations of isolated words, sentences and passages. Research on Speech Perception, 17, 285–301.

    Google Scholar 

  • Braun, A. (1991). Speaking while intoxicated: Phonetic and forensic aspects. In Proceedings of the XIIth international congress of phonetic sciences, Aix-en-Provence, pp. 146–149.

  • Burger, S., Weilhammer, K., Schiel, F., & Tillmann, H. G. (2000). Verbmobil data collection and annotation. In Wahlster, W. (Eds.), Verbmobil: foundations of speech-to-speech translation. Springer, Berlin, pp. 537–549.

    Google Scholar 

  • Bund gegen Alkohol und Drogen im Strassenverkehr. URL http://www.bads.de/Alkohol/statistik.htm. Cited 2009-03-23.

  • Cassidy, S., & Harrington, J. (2001) Multi-level annotation in the EMU speech database management system. Speech Communication, 33(1–2): 61–77.

    Article  Google Scholar 

  • Cooney, O. M., McGuigan, K., Murphy, P., & Conroy, R. (1998). Acoustic analysis of the effects of alcohol on the human voice. The Journal of the Acoustical Society of America, p. 2895.

  • Dhillon, I. (2009). Variation der Grundfrequenz in alkoholisierter Sprache. Thesis magister artium, Ludwig-Maximilians-Universität München.

  • Draxler, C., & Jänsch, K. (2004). SpeechRecorder—a universal platform independent multi-channel audio recording software. In Proceedings of the LREC. Lisbon, Portugal.

  • Draxler, C. (2005). WebTranscribe—an extensible web-based speech annotation framework. In Proceedings of TSD 2005, pp. 61–68.

  • Grabe, E., & Low, E. L. (2004). Durational variability in speech and the rhythm class hypothesis. In Gussenhoven, C., & Warner, N. (Eds.) Papers in laboratory phonology 7, Berlin, New York, Mouton de Gruyter.

  • Hansen, J. H. L., & Patil, S. (2007). Speech under stress: Analysis, modeling and recognition. In: Müller, C. (Eds.), Speaker Classification I, LNAI 4343, pp. 108–137.

  • Hollien, H., De Jong, G., Martin, C. A., Schwartz, R., & Liljegren, K. (2001). Effects of ethanol intoxication on speech suprasegmentals. The Journal of the Acoustical Society of America, pp. 3198–3206.

  • Johnson, K., Pisoni, D. B., & Bernacki, R. H. (1990). Do voice recordings reveal whether a person is intoxicated? A case study. Phonetica, 41, 215–237.

    Article  Google Scholar 

  • Kipp, A., Wesenick, B., & Schiel, F. (1997). Pronunciation modeling applied to automatic segmentation of spontaneous speech. In Proceedings of the EUROSPEECH, pp. 1023–1026.

  • Klingholz, F., Penning, R., & Liebhardt, E. (1988) Recognition of low-level alcohol intoxication from speech signal. The Journal of the Acoustical Society of America, pp. 929–935.

  • Künzel, H. J., & Braun, A. (2003). The effect of alcohol on speech prosody. In Proceedings of the ICPhS. Barcelona, pp. 2645–2648.

  • Künzel, H. J., Braun, A., & Eysholdt U. (1992). Einfluß von Alkohol auf Sprache und Stimme. Heidelberg: Kriminalistik Verlag.

    Google Scholar 

  • Leisch, F. (2009). personal communication with Friedrich Leisch, computational statistics. Ludwig-Maximilians-Universität, München.

    Google Scholar 

  • Levit, M., Huber, R., Batliner, A., & Nöth, E. (2001). Use of prosodic speech characteristics for automated detection of alcohol intoxication. In Bacchiani, M., Hirschberg, J., Litman, D., & Ostendorf, M. (Eds.), Proceedings of the workshop on prosody and speech recognition 2001, Red Bank, NJ, pp. 103–106.

  • Martin, C. S., & Yuchtman, M. (1986). Using speech as an index of alcohol-intoxication. Research on Speech Perception, 12, 413–426.

    Google Scholar 

  • Mögele, H., Kaiser, M., & Schiel, F. (2006). SmartWeb UMTS speech data collection: The SmartWeb handheld corpus. In Proceedings of the LREC 2006, Genova, Italy, pp. 2106–2111.

  • Large German Pronunciation Dictionary PHONOLEX. URL http://www.bas.uni-muenchen.de/Bas/BasPHONOLEXeng.html. Cited 2012-12-01.

  • R Development Core Team. (2005). R, a language and environment for statistical computing. Reference index version 2.9.0. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0, URL http://www.R-project.org.

  • Ramus, F., Nespor, M., & Mehler, J. (1999). Correlates of linguistic rhythm in the speech signal. Cognition, 73 (3), 265–292, Elsevier.

    Google Scholar 

  • Reichel, U. D., & Schiel, F. (2005). Using morphology and phoneme history to improve Grapheme-to-Phoneme conversion. In Proceedings of the EUROSPEECH, pp. 1937–1940.

  • Schiel, F. (1999). Automatic phonetic transcription of non-prompted speech. In Proceedings of the ICPhS. San Francisco, August 1999, pp. 607–610.

  • Schiel, F., & Heinrich, C. (2009). Laying the Foundation for in-car alcohol detection by speech. In Proceedings of the INTERSPEECH 2009, Brighton, UK, pp. 983–986.

  • Schiel, F., Heinrich, C., & Neumeyer, V. (2010). Rhythm and formant features for automatic alcohol detection. In Proceedings of the INTERSPEECH 2010, Chiba, Japan, pp. 458-461.

  • Schötz S. (2007) Acoustic analysis of adult speaker age. In Müller, C. (Eds.) Speaker classification I, LNAI 434, Springer, pp. 88–107.

  • SpeechDat Deliverable SD1.3.2 : Specification of orthographic transcription and lexicon conventions. URL http://www.speechdat.org/speechdat/deliverables/public/SD132V24.PDF. Cited 2010-12-01.

  • Sobell, L. C., Sobell, M. B., & Coleman, R. F. (1982). Alcohol-inducted disfluency in non-alcoholics. Folia Phoniatrica, 34, 316–323.

    Article  Google Scholar 

  • Statistisches Bundesamt, Wiesbaden, Germany (2007). Alkoholunfälle 2007. e.g. URL http://www.bads.de/Statistikdaten/Alkohol/AlkVU%202007.pdf. Cited 2010-12-01.

  • Traunmüller, H. (1997). Perception of speaker sex, age, and vocal effort. Phonum, 4, 183–186.

    Google Scholar 

  • Trojan, F., & Kryspin-Exner, K. (1968). The decay of articulation under the influence of alcohol and paraldehyde. Folia Phoniatrica 20, 217–238.

    Article  Google Scholar 

  • Watanabe, H., Shin, T., Matsuo, H., Okuno, F., Tsuji, T., Matsuoka, M., Fukaura, J., & Matsunaga, H. (1994). Studies on vocal fold injection and changes in pitch associated with alcohol intake. Journal of Voice 340–346.

  • Watson P. E., Watson R., & Batt R. D. (1980). Total body water volumes for adult males and females estimated from simple anthropometric measurements. The American Journal of Clinical Nutrition, 33, 27–39.

    Google Scholar 

  • Wells, J. C. (1997). SAMPA computer readable phonetic alphabet. In Gibbon, D., Moore, R., & Winski, R. (Eds.) Handbook of standards and resources for spoken language systems. Berlin and New York: Mouton de Gruyter, pp. 11–12.

    Google Scholar 

  • Widmark, E. M. P. (1932). Die theoretischen Grundlagen und die praktische Verwendbarkeit der gerichtlich-medizinischen Alkoholbestimmung. Berlin, Wien: Verlag Urban und Schwarzenberg.

    Google Scholar 

  • Wu K (1991) Gender recognition from speech. Part I: Coarse analysis. The Journal of the Acoustical Society of America, 90(4), 1828–1840.

    Article  Google Scholar 

Download references

Acknowledgments

ALC was made possible by funding of the Bavarian Archive for Speech Signals, the Institute for Legal Medicine (Prof. Thomas Gilg) and the ‘Bund gegen Alkohol und Drogen im Strassenverkehr’. The recording software SpeechRecorder was supplied by Klaus Jänsch and Christoph Draxler. The authors would like to thank all colleagues of the Institute of Phonetics and Speech Processing at the Ludwig-Maximilians-Universität (Prof. J. Harrington) for their valuable support as well as the students and technicians who were directly involved in this endeavor, namely Veronika Neumeyer, Indra Dhillon and Christian Gruttauer.

Author information

Authors and Affiliations

  1. Bavarian Archive for Speech Signals, Ludwig-Maximilians-Universität München, Schellingstr. 3, 80799, München, Germany

    Florian Schiel, Christian Heinrich & Sabine Barfüsser

Authors
  1. Florian Schiel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Christian Heinrich
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sabine Barfüsser
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Florian Schiel.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Schiel, F., Heinrich, C. & Barfüsser, S. Alcohol language corpus: the first public corpus of alcoholized German speech. Lang Resources & Evaluation 46, 503–521 (2012). https://doi.org/10.1007/s10579-011-9139-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10579-011-9139-y

Keywords

Search

Navigation