---
title: "Can Prosody Aid the Automatic Classification of Dialog Acts in"
description: "The paper asks whether prosody, meaning the timing, pitch and energy of speech independent of the… 57 references, cited by 49 papers here."
authors: ["E. Shriberg", "R. Bates", "A. Stolcke", "P. Taylor", "D. Jurafsky", "K. Ries", "N. Coccaro", "R. Martin", "M. Meteer", "C. Van Ess-Dykema"]
year: 1998
venue: "Language and Speech 41(3-4), 439-487, 1998"
source: "https://arxiv.org/abs/cs/0006024"
doi: "10.48550/arxiv.cs/0006024"
arxiv: "cs/0006024"
licence: "arXiv non-exclusive distribution licence (read only, no redistribution)"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/shriberg-2000-prosody-aid-automatic-classification-dialog/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shriberg-2000-prosody-aid-automatic-classification-dialog/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1998](https://md.research.elamur.ai/free/en/papers/1998/) / Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech?

# Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech?

**Authors:** [E. Shriberg](https://md.research.elamur.ai/free/en/authors/elizabeth-shriberg/), [R. Bates](https://md.research.elamur.ai/free/en/authors/rebecca-bates/), [A. Stolcke](https://md.research.elamur.ai/free/en/authors/andreas-stolcke/), P. Taylor, [D. Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/), K. Ries, [N. Coccaro](https://md.research.elamur.ai/free/en/authors/noah-coccaro/), R. Martin, [M. Meteer](https://md.research.elamur.ai/free/en/authors/marie-w-meteer/) and C. Van Ess-Dykema · **Year:** 1998 · **Venue:** Language and Speech 41(3-4), 439-487, 1998 · **Publisher:** [SAGE Publishing](https://md.research.elamur.ai/free/en/publishers/sage-publishing/) · **Licence:** [arXiv non-exclusive distribution licence (read only, no redistribution)](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/cs/0006024) · [PDF](https://arxiv.org/pdf/cs/0006024) · [DOI 10.48550/arxiv.cs/0006024](https://doi.org/10.48550/arxiv.cs/0006024) · [arXiv cs/0006024](https://arxiv.org/abs/cs/0006024) · [OpenAlex](https://openalex.org/W2112078429)

**Citations:** 307 citations (OpenAlex, 2026-10-14) · [49](https://md.research.elamur.ai/free/en/papers/shriberg-2000-prosody-aid-automatic-classification-dialog/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks whether prosody, meaning the timing, pitch and energy of speech independent of the words, can help a machine decide which dialog act (DA) an utterance performs: a statement, a question, a backchannel, and so on. Earlier DA classifiers relied almost entirely on lexical cues such as cue phrases, N-grams and syntactic form. The authors used over 1000 hand-labelled Switchboard conversations, annotated with the SWBD-DAMSL tag-set. For each DA they automatically extracted duration, pause, F0, energy and speaking-rate features and trained decision trees on them. They tested these trees alone and combined with DA-specific statistical language models, using either reference transcripts or speech recognizer output. Prosody helped significantly on an overall task and on three subtasks. The gain from adding prosody was largest when the words came from the recognizer. Because the cues overlap heavily, removing one feature type let others compensate. The work shows that DAs are marked redundantly in natural talk, which makes cheap acoustic signals a practical complement to words.

## Key points
- Data: more than 1000 Switchboard telephone conversations, with DAs hand-annotated using the SWBD-DAMSL scheme. Prosodic features were extracted automatically per DA, assuming known utterance boundaries.
- Model: decision trees over prosodic features, evaluated with equal class priors, then integrated with DA-specific N-gram language models. Tests used both true words and ASR output; the ASR word error rate for conversational speech was above 30%.
- Feature analyses showed that the expected cues mattered, for example F0 for questions. However, less obvious features took over when the canonical ones were removed, and the most useful features differed from task to task.
- An oracle experiment from the WS97 project conditioned the language model on the correct DA. Overall word error barely moved (41.2% → 40.9%), because about 83% of test words fall inside Statements. Word error for Backchannels and No-Answers still fell by 7% and 18%.
- The authors argue for a sequential pipeline: first segment utterances independently of DA, then label them. Prior joint A* search had brought little benefit over this approach.

## Interesting ideas
- Train a separate, interpretable classifier on non-lexical cues and combine it with a per-class language model, rather than feeding everything into one opaque model; each source's contribution stays measurable.
- Ablate whole feature families and check whether other features compensate; this reveals redundancy instead of assuming one canonical cue is essential.
- Report accuracy under equal class priors, so that a dominant class (Statements here) cannot hide failure on rare but important classes.
- Run an oracle upper-bound experiment, giving the downstream module the gold value of an upstream label, to see whether improving that label is worth the effort, and analyse the result per class.
- Segment first in a class-independent way, then label; joint search added little and kept the components separable.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): The speech-act detector in prag could score form cues (punctuation, word order, auxiliaries, intonation-like markers such as "?" on declaratives) separately from lexical cue words. It could then combine the two scores, so every act label shows which evidence decided it.
- **I2** (learn): Evaluation could switch off cue groups, for example dropping question marks or wh-words, and measure how speech-act and parse decisions degrade. This shows where Mova depends on a single fragile signal.
- **I3** (answer): Test suites for readers and students could report per-question-type and prior-balanced scores. Rare types such as yes/no or negative questions would then not be masked by easy majority items.
- **I4** (learn): Before investing in better speech-act or frame detection, Mova could feed gold labels to the world/answer stages. Measuring the per-category gain shows which upstream improvements actually pay off.
- **I5** (tokens): Sentence and utterance splitting in the en crate can stay independent of later act classification. This keeps the stages simple and individually explainable without losing accuracy.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 539 works · 179,533 citations
- [University of Edinburgh](https://md.research.elamur.ai/free/en/universities/university-of-edinburgh/) — University, Edinburgh, United Kingdom · 359 works · 77,352 citations
- [Johns Hopkins University](https://md.research.elamur.ai/free/en/universities/johns-hopkins-university/) — University, Baltimore, United States · 240 works · 96,487 citations
- [University of Colorado Boulder](https://md.research.elamur.ai/free/en/universities/university-of-colorado-boulder/) — University, Boulder, United States · 69 works · 51,069 citations
- [SRI International](https://md.research.elamur.ai/free/en/labs/sri-international/) — Research institute, Menlo Park, United States · 23 works · 7,208 citations
- [Boston University](https://md.research.elamur.ai/free/en/universities/boston-university/) — University, Boston, United States · 26 works · 4,022 citations
- [United States Department of Defense](https://md.research.elamur.ai/free/en/government/united-states-department-of-defense/) — Government body, Washington, United States · 4 works · 1,907 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (3): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 624 works · [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 480 works · [💬 Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · 229 works

## Cite

Cite as: E. Shriberg, R. Bates, A. Stolcke, P. Taylor, D. Jurafsky, K. Ries, N. Coccaro, R. Martin, M. Meteer and C. Van Ess-Dykema. 1998. Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech?. Language and Speech 41(3-4), 439-487, 1998.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{shriberg1998can,
  title = {{Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech?}},
  author = {E. Shriberg, R. Bates, A. Stolcke, P. Taylor, D. Jurafsky, K. Ries, N. Coccaro, R. Martin, M. Meteer and C. {Van Ess-Dykema}},
  booktitle = {Language and Speech 41(3-4), 439-487, 1998},
  year = {1998},
  doi = {10.48550/arxiv.cs/0006024},
  eprint = {cs/0006024},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.cs/0006024}
}
```

- [← previous Robust Pronoun Resolution with Limited Knowledge](https://md.research.elamur.ai/free/en/papers/mitkov-1998-robust-pronoun-resolution-limited-knowledge/)
- [next → Algorithms for Scoring Coreference Chains](https://md.research.elamur.ai/free/en/papers/bagga-1998-algorithms-scoring-coreference-chains/)
- [↑ back to papers of 1998](https://md.research.elamur.ai/free/en/papers/1998/)

## References

57 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Finke, M., Lapata, M., Lavie, A., Levin, L., Tomokiyo, L. M., Polzin, T., Ries, K., Waibel, A., & Zechner, K. (1998). Clarity: Inferring discourse structure from speech. In J. Chu-Carroll & N. Green (Eds.), Applying Machine Learning to Discourse Processing. Papers from the 1998 AAAI Spring Symposium. Technical Report SS-98-01 (pp. 25–32). Menlo Park, CA: AAAI Press. [find](https://scholar.google.com/scholar?q=Finke%2C+M%2E%2C+Lapata%2C+M%2E%2C+Lavie%2C+A%2E%2C+Levin%2C+L%2E%2C+Tomokiyo%2C+L%2E+M%2E%2C+Polzin%2C+T%2E%2C+Ries%2C+K%2E%2C+Waibel%2C+A%2E%2C+%26+Zechner%2C+K%2E+%281998%29%2E+Clarity%3A+Inferring+discourse+structure+from+speech%2E+In+J%2E+Chu%2DCarroll+%26+N%2E+Green+%28)
2. Godfrey, J., Holliman, E., & McDaniel, J. (1992). SWITCHBOARD: Telephone speech corpus for research and development. In Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing (Vol. 1, pp. 517–520). San Francisco. [find](https://scholar.google.com/scholar?q=Godfrey%2C+J%2E%2C+Holliman%2C+E%2E%2C+%26+McDaniel%2C+J%2E+%281992%29%2E+SWITCHBOARD%3A+Telephone+speech+corpus+for+research+and+development%2E+In+Proceedings+of+the+IEEE+Conference+on+Acoustics%2C+Speech%2C+and+Signal+Processing+%28)
3. Grosz, B., & Hirschberg, J. (1992). Some intonational characteristics of discourse structure. In J. J. Ohala, T. M. Nearey, B. L. Derwing, M. M. Hodge, & G. E. Wiebe (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 1, pp. 429–432). Banff, Canada. [find](https://scholar.google.com/scholar?q=Grosz%2C+B%2E%2C+%26+Hirschberg%2C+J%2E+%281992%29%2E+Some+intonational+characteristics+of+discourse+structure%2E+In+J%2E+J%2E+Ohala%2C+T%2E+M%2E+Nearey%2C+B%2E+L%2E+Derwing%2C+M%2E+M%2E+Hodge%2C+%26+G%2E+E%2E+Wiebe+%28Eds%2E%29%2C+Proceedings+of+the+Interna)
4. Haan, J., van Heuven, V. J., Pacilly, J. J. A., & van Bezooijen, R. (1997a). Intonational characteristics of declarativity and interrogativity in Dutch: A comparison. In A. Botonis, G. Kouroupetroglou, & G. Carayiannis (Eds.), ESCA Workshop on Intonation: Theory, Models and Applications (pp. 173–176). Athens, Greece. [find](https://scholar.google.com/scholar?q=Haan%2C+J%2E%2C+van+Heuven%2C+V%2E+J%2E%2C+Pacilly%2C+J%2E+J%2E+A%2E%2C+%26+van+Bezooijen%2C+R%2E+%281997a%29%2E+Intonational+characteristics+of+declarativity+and+interrogativity+in+Dutch%3A+A+comparison%2E+In+A%2E+Botonis%2C+G%2E+Kouroupetroglou)
5. Haan, J., van Heuven, V. J., Pacilly, J. J. A., & van Bezooijen, R. (1997b). An anatomy of Dutch question intonation. In H. de Hoop & M. den Dikken (Eds.), Linguistics in the Netherlands. Amsterdam: John Benjamins. [↗](https://doi.org/10.1075/avt.14.11haa)
6. Hirschberg, J., & Nakatani, C. (1996). A prosodic analysis of discourse segments in direction-giving monologues. In Proc. ACL (pp. 286–293). Santa Cruz, CA. [find](https://scholar.google.com/scholar?q=Hirschberg%2C+J%2E%2C+%26+Nakatani%2C+C%2E+%281996%29%2E+A+prosodic+analysis+of+discourse+segments+in+direction%2Dgiving+monologues%2E+In+Proc%2E+ACL+%28pp%2E+286%E2%80%93293%29%2E+Santa+Cruz%2C+CA%2E)
7. Hirschberg, J., & Nakatani, C. H. (1998). Using machine learning to identify intonational segments. In J. Chu-Carroll & N. Green (Eds.), Applying Machine Learning to Discourse Processing. Papers from the 1998 AAAI Spring Symposium. Technical Report SS-98-01 (pp. 52–59). Menlo Park, CA: AAAI Press. [find](https://scholar.google.com/scholar?q=Hirschberg%2C+J%2E%2C+%26+Nakatani%2C+C%2E+H%2E+%281998%29%2E+Using+machine+learning+to+identify+intonational+segments%2E+In+J%2E+Chu%2DCarroll+%26+N%2E+Green+%28Eds%2E%29%2C+Applying+Machine+Learning+to+Discourse+Processing%2E+Papers+from+)
8. Jordan, M. I., & Jacobs, R. A. (1994). Hierarchical mixtures of experts and the EM algorithm. Neural Computation, 6(2), 181–214. [↗](https://doi.org/10.1162/neco.1994.6.2.181)
9. Jurafsky, D., Bates, R., Coccaro, N., Martin, R., Meteer, M., Ries, K., Shriberg, E., Stolcke, A., Taylor, P., & Van Ess-Dykema, C. (1997a). Automatic detection of discourse structure for speech recognition and understanding. In IEEE Workshop on Speech Recognition and Understanding. Santa Barbara, CA. [↗](https://doi.org/10.5445/ir/1000166547)
10. Jurafsky, D., Shriberg, E., & Biasca, D. (1997b). Switchboard-DAMSL Labeling Project Coder’s Manual (Tech. Rep. No. 97-02). University of Colorado Institute of Cognitive Science. ([http://stripe.colorado.edu/˜jurafsky/manual.august1.html](http://stripe.colorado.edu/˜jurafsky/manual.august1.html)) [↗](http://stripe.colorado.edu/˜jurafsky/manual.august1.html)
11. Jurafsky, D., Shriberg, E., Fox, B., & Curl, T. (1998a). [Lexical, prosodic, and syntactic cues for dialog acts](https://md.research.elamur.ai/free/en/papers/jurafsky-1998-lexical-prosodic-syntactic-cues-dialog/). In Proceedings of the COLING-ACL Workshop on Discourse Relations and Discourse Markers (pp. 114–120). Montreal.
12. Jurafsky, D., Bates, R., Coccaro, N., Martin, R., Meteer, M., Ries, K., Shriberg, E., Stolcke, A., Taylor, P., & Van Ess-Dykema, C. (1998b). Switchboard Discourse Language Modeling Project Report (Research Note No. 30). Baltimore, MD: Center for Speech and Language Processing, Johns Hopkins University. [find](https://scholar.google.com/scholar?q=Jurafsky%2C+D%2E%2C+Bates%2C+R%2E%2C+Coccaro%2C+N%2E%2C+Martin%2C+R%2E%2C+Meteer%2C+M%2E%2C+Ries%2C+K%2E%2C+Shriberg%2C+E%2E%2C+Stolcke%2C+A%2E%2C+Taylor%2C+P%2E%2C+%26+Van+Ess%2DDykema%2C+C%2E+%281998b%29%2E+Switchboard+Discourse+Language+Modeling+Project+Report+%28Res)
13. Katz, S. M. (1987). Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Transactions on Acoustics, Speech, and Signal Processing, 35(3), 400–401. [↗](https://doi.org/10.1109/tassp.1987.1165125)
14. Kießling, A., Kompe, R., Niemann, H., Nöth, E., & Batliner, A. (1993). “Roger”, “Sorry”, “I’m still listening”: Dialog guiding signals in informational retrieval dialogs. In D. House & P. Touati (Eds.), ESCA Workshop on Prosody (pp. 140–143). Lund, Sweden. [find](https://scholar.google.com/scholar?q=Kie%C3%9Fling%2C+A%2E%2C+Kompe%2C+R%2E%2C+Niemann%2C+H%2E%2C+No%CC%88th%2C+E%2E%2C+%26+Batliner%2C+A%2E+%281993%29%2E+%E2%80%9CRoger%E2%80%9D%2C+%E2%80%9CSorry%E2%80%9D%2C+%E2%80%9CI%E2%80%99m+still+listening%E2%80%9D%3A+Dialog+guiding+signals+in+informational+retrieval+dialogs%2E+In+D%2E+House+%26+P%2E+Touati+%28Eds)
15. Kita, K., Fukui, Y., Nagata, M., & Morimoto, T. (1996). Automatic acquisition of probabilistic dialogue models. In H. T. Bunnell & W. Idsardi (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 1, pp. 196–199). Philadelphia. [find](https://scholar.google.com/scholar?q=Kita%2C+K%2E%2C+Fukui%2C+Y%2E%2C+Nagata%2C+M%2E%2C+%26+Morimoto%2C+T%2E+%281996%29%2E+Automatic+acquisition+of+probabilistic+dialogue+models%2E+In+H%2E+T%2E+Bunnell+%26+W%2E+Idsardi+%28Eds%2E%29%2C+Proceedings+of+the+International+Conference+on+Spo)
16. Kompe, R. (1997). Prosody in Speech Understanding Systems. Berlin: Springer. [find](https://scholar.google.com/scholar?q=Kompe%2C+R%2E+%281997%29%2E+Prosody+in+Speech+Understanding+Systems%2E+Berlin%3A+Springer%2E)
17. Kompe, R., Kießling, A., Niemann, H., Nöth, E., Schukat-Talamazzini, E., Zottmann, A., & Batliner, A. (1995). Prosodic scoring of word hypotheses graphs. In J. M. Pardo, E. Enríquez, J. Ortega, J. Ferreiros, J. Macías, & F. J. Valverde (Eds.), Proceedings of the 4th European Conference on Speech Communication and Technology (Vol. 2, pp. 1333–1336). Madrid. [↗](https://doi.org/10.22028/d291-25178)
18. Koopmans-van Beinum, F. J., & van Donzel, M. E. (1996). Relationship between discourse structure and dynamic speech rate. In H. T. Bunnell & W. Idsardi (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 3, pp. 1724–1727). Philadelphia. [find](https://scholar.google.com/scholar?q=Koopmans%2Dvan+Beinum%2C+F%2E+J%2E%2C+%26+van+Donzel%2C+M%2E+E%2E+%281996%29%2E+Relationship+between+discourse+structure+and+dynamic+speech+rate%2E+In+H%2E+T%2E+Bunnell+%26+W%2E+Idsardi+%28Eds%2E%29%2C+Proceedings+of+the+International+Confere)
19. Levelt, W. J. M. (1989). Speaking: From Intention to Articulation. Cambridge, MA: MIT Press. [find](https://scholar.google.com/scholar?q=Levelt%2C+W%2E+J%2E+M%2E+%281989%29%2E+Speaking%3A+From+Intention+to+Articulation%2E+Cambridge%2C+MA%3A+MIT+Press%2E)
20. Litman, D. J., & Passonneau, R. J. (1995). Combining multiple knowledge sources for discourse segmentation. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (pp. 108–115). MIT, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Litman%2C+D%2E+J%2E%2C+%26+Passonneau%2C+R%2E+J%2E+%281995%29%2E+Combining+multiple+knowledge+sources+for+discourse+segmentation%2E+In+Proceedings+of+the+33rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28)
21. Mast, M., Kompe, R., Harbeck, S., Kießling, A., Niemann, H., Nöth, E., Schukat-Talamazzini, E. G., & Warnke, V. (1996). Dialog act classification with the help of prosody. In H. T. Bunnell & W. Idsardi (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 3, pp. 1732–1735). Philadelphia. [find](https://scholar.google.com/scholar?q=Mast%2C+M%2E%2C+Kompe%2C+R%2E%2C+Harbeck%2C+S%2E%2C+Kie%C3%9Fling%2C+A%2E%2C+Niemann%2C+H%2E%2C+No%CC%88th%2C+E%2E%2C+Schukat%2DTalamazzini%2C+E%2E+G%2E%2C+%26+Warnke%2C+V%2E+%281996%29%2E+Dialog+act+classification+with+the+help+of+prosody%2E+In+H%2E+T%2E+Bunnell+%26+W%2E+Idsar)
22. Meteer, M., Taylor, A., MacIntyre, R., & Iyer, R. (1995). Dysfluency Annotation Stylebook for the Switchboard Corpus. Linguistic Data Consortium. (Revised June 1995 by Ann Taylor. ftp://ftp.cis.upenn.edu/pub/treebank/swbd/doc/DFL-book.ps.gz) [find](https://scholar.google.com/scholar?q=Meteer%2C+M%2E%2C+Taylor%2C+A%2E%2C+MacIntyre%2C+R%2E%2C+%26+Iyer%2C+R%2E+%281995%29%2E+Dysfluency+Annotation+Stylebook+for+the+Switchboard+Corpus%2E+Linguistic+Data+Consortium%2E+%28Revised+June+1995+by+Ann+Taylor%2E+ftp%3A%2F%2Fftp%2Ecis%2Eupenn%2E)
23. Morgan, N., & Fossler-Lussier, E. (1998). Combining multiple estimators of speaking rate. In Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing (Vol. 2, pp. 729–732). Seattle, WA. [find](https://scholar.google.com/scholar?q=Morgan%2C+N%2E%2C+%26+Fossler%2DLussier%2C+E%2E+%281998%29%2E+Combining+multiple+estimators+of+speaking+rate%2E+In+Proceedings+of+the+IEEE+Conference+on+Acoustics%2C+Speech%2C+and+Signal+Processing+%28Vol%2E+2%2C+pp%2E+729%E2%80%93732%29%2E+Seatt)
24. Morgan, N., Fosler, E., & Mirghafori, N. (1997). Speech recognition using on-line estimation of speaking rate. In G. Kokkinakis, N. Fakotakis, & E. Dermatas (Eds.), Proceedings of the 5th European Conference on Speech Communication and Technology (Vol. 4, pp. 2079–2082). Rhodes, Greece. [find](https://scholar.google.com/scholar?q=Morgan%2C+N%2E%2C+Fosler%2C+E%2E%2C+%26+Mirghafori%2C+N%2E+%281997%29%2E+Speech+recognition+using+on%2Dline+estimation+of+speaking+rate%2E+In+G%2E+Kokkinakis%2C+N%2E+Fakotakis%2C+%26+E%2E+Dermatas+%28Eds%2E%29%2C+Proceedings+of+the+5th+European+Con)
25. Nagata, M., & Morimoto, T. (1994). First steps toward statistical modeling of dialogue to predict the speech act type of the next utterance. Speech Communication, 15, 193–203. [find](https://scholar.google.com/scholar?q=Nagata%2C+M%2E%2C+%26+Morimoto%2C+T%2E+%281994%29%2E+First+steps+toward+statistical+modeling+of+dialogue+to+predict+the+speech+act+type+of+the+next+utterance%2E+Speech+Communication%2C+15%2C+193%E2%80%93203%2E)
26. Nakajima, S., & Allen, J. F. (1993). A study on prosody and discourse structure in cooperative dialogues. Phonetica, 50, 197–210. [↗](https://doi.org/10.1159/000261940)
27. Nakajima, S., & Tsukada, H. (1997). Prosodic features of utterances in task-oriented dialogues. In Y. Sagisaka, N. Campbell, & N. Higuchi (Eds.), Computing Prosody: Computational Models for Processing Spontaneous Speech (pp. 81–94). New York: Springer. [↗](https://doi.org/10.1007/978-1-4612-2258-3_7)
28. Neumeyer, L., & Weintraub, M. (1994). Microphone-independent robust signal processing using probabilistic optimum filtering. In Proceedings of the ARPA Workshop on Human Language Technology (pp. 336–341). Plainsboro, NJ. [find](https://scholar.google.com/scholar?q=Neumeyer%2C+L%2E%2C+%26+Weintraub%2C+M%2E+%281994%29%2E+Microphone%2Dindependent+robust+signal+processing+using+probabilistic+optimum+filtering%2E+In+Proceedings+of+the+ARPA+Workshop+on+Human+Language+Technology+%28pp%2E+336%E2%80%933)
29. Neumeyer, L., & Weintraub, M. (1995). Robust speech recognition in noise using adaptation and mapping techniques. In Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing (Vol. 1, pp. 141–144). Detroit. [find](https://scholar.google.com/scholar?q=Neumeyer%2C+L%2E%2C+%26+Weintraub%2C+M%2E+%281995%29%2E+Robust+speech+recognition+in+noise+using+adaptation+and+mapping+techniques%2E+In+Proceedings+of+the+IEEE+Conference+on+Acoustics%2C+Speech%2C+and+Signal+Processing+%28Vol)
30. Nöth, E. (1991). Prosodische Information in der automatischen Spracherkennung — Berechnung und Anwendung. Tübingen: Niemeyer. [↗](https://doi.org/10.1515/9783111353814)
31. Ostendorf, M., & Ross, K. (1997). Multi-level recognition of intonation labels. In Y. Sagisaka, N. Campbell, & N. Higuchi (Eds.), Computing Prosody: Computational Models for Processing Spontaneous Speech (pp. 291–308). New York: Springer. [find](https://scholar.google.com/scholar?q=Ostendorf%2C+M%2E%2C+%26+Ross%2C+K%2E+%281997%29%2E+Multi%2Dlevel+recognition+of+intonation+labels%2E+In+Y%2E+Sagisaka%2C+N%2E+Campbell%2C+%26+N%2E+Higuchi+%28Eds%2E%29%2C+Computing+Prosody%3A+Computational+Models+for+Processing+Spontaneous+Spe)
32. Quirk, R., Greenbaum, S., Leech, G., & Svartvik, J. (1985). A Comprehensive Grammar of the English Language. London: Longman. [find](https://scholar.google.com/scholar?q=Quirk%2C+R%2E%2C+Greenbaum%2C+S%2E%2C+Leech%2C+G%2E%2C+%26+Svartvik%2C+J%2E+%281985%29%2E+A+Comprehensive+Grammar+of+the+English+Language%2E+London%3A+Longman%2E)
33. Reithinger, N., & Klesen, M. (1997). Dialog act classification using language models. In G. Kokkinakis, N. Fakotakis, & E. Dermatas (Eds.), Proceedings of the 5th European Conference on Speech Communication and Technology (Vol. 4, pp. 2235–2238). Rhodes, Greece. [find](https://scholar.google.com/scholar?q=Reithinger%2C+N%2E%2C+%26+Klesen%2C+M%2E+%281997%29%2E+Dialog+act+classification+using+language+models%2E+In+G%2E+Kokkinakis%2C+N%2E+Fakotakis%2C+%26+E%2E+Dermatas+%28Eds%2E%29%2C+Proceedings+of+the+5th+European+Conference+on+Speech+Communi)
34. Reithinger, N., & Maier, E. (1995). [Utilizing statistical dialogue act processing in Verbmobil](https://md.research.elamur.ai/free/en/papers/reithinger-1995-utilizing-statistical-dialogue-act-processing/). In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (pp. 116–121). MIT, Cambridge, MA. [↗](https://doi.org/10.48550/arxiv.cmp-lg/9505013)
35. Reithinger, N., Engel, R., Kipp, M., & Klesen, M. (1996). Predicting dialogue acts for a speech-to-speech translation system. In H. T. Bunnell & W. Idsardi (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 2, pp. 654–657). Philadelphia. [↗](https://doi.org/10.22028/d291-25293)
36. Samuel, K., Carberry, S., & Vijay-Shanker, K. (1998). [Computing dialogue acts from features with transformation-based learning](https://md.research.elamur.ai/free/en/papers/samuel-1998-computing-dialogue-acts-features-transformation/). In J. Chu-Carroll & N. Green (Eds.), Applying Machine Learning to Discourse Processing. Papers from the 1998 AAAI Spring Symposium. Technical Report SS-98-01 (pp. 90–97). Menlo Park, CA: AAAI Press. [↗](https://doi.org/10.48550/arxiv.cmp-lg/9806002)
37. Shriberg, E., Bates, R., & Stolcke, A. (1997). A prosody-only decision-tree model for disfluency detection. In G. Kokkinakis, N. Fakotakis, & E. Dermatas (Eds.), Proceedings of the 5th European Conference on Speech Communication and Technology (Vol. 5, pp. 2383–2386). Rhodes, Greece. [find](https://scholar.google.com/scholar?q=Shriberg%2C+E%2E%2C+Bates%2C+R%2E%2C+%26+Stolcke%2C+A%2E+%281997%29%2E+A+prosody%2Donly+decision%2Dtree+model+for+disfluency+detection%2E+In+G%2E+Kokkinakis%2C+N%2E+Fakotakis%2C+%26+E%2E+Dermatas+%28Eds%2E%29%2C+Proceedings+of+the+5th+European+Confer)
38. Siegel, S., & Castellan, N. J., Jr. (1988). Nonparametric Statistics for the Behavioral Sciences (Second ed.). New York: McGraw-Hill. [find](https://scholar.google.com/scholar?q=Siegel%2C+S%2E%2C+%26+Castellan%2C+N%2E+J%2E%2C+Jr%2E+%281988%29%2E+Nonparametric+Statistics+for+the+Behavioral+Sciences+%28Second+ed%2E%29%2E+New+York%3A+McGraw%2DHill%2E)
39. Stolcke, A., & Shriberg, E. (1996). Automatic linguistic segmentation of conversational speech. In H. T. Bunnell & W. Idsardi (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 2, pp. 1005–1008). Philadelphia. [find](https://scholar.google.com/scholar?q=Stolcke%2C+A%2E%2C+%26+Shriberg%2C+E%2E+%281996%29%2E+Automatic+linguistic+segmentation+of+conversational+speech%2E+In+H%2E+T%2E+Bunnell+%26+W%2E+Idsardi+%28Eds%2E%29%2C+Proceedings+of+the+International+Conference+on+Spoken+Language+Pro)
40. Stolcke, A., Shriberg, E., Bates, R., Coccaro, N., Jurafsky, D., Martin, R., Meteer, M., Ries, K., Taylor, P., & Van Ess-Dykema, C. (1998). Dialog act modeling for conversational speech. In J. Chu-Carroll & N. Green (Eds.), Applying Machine Learning to Discourse Processing. Papers from the 1998 AAAI Spring Symposium. Technical Report SS-98-01 (pp. 98–105). Menlo Park, CA: AAAI Press. [find](https://scholar.google.com/scholar?q=Stolcke%2C+A%2E%2C+Shriberg%2C+E%2E%2C+Bates%2C+R%2E%2C+Coccaro%2C+N%2E%2C+Jurafsky%2C+D%2E%2C+Martin%2C+R%2E%2C+Meteer%2C+M%2E%2C+Ries%2C+K%2E%2C+Taylor%2C+P%2E%2C+%26+Van+Ess%2DDykema%2C+C%2E+%281998%29%2E+Dialog+act+modeling+for+conversational+speech%2E+In+J%2E+Chu%2DCar)
41. Suhm, B., & Waibel, A. (1994). Toward better language models for spontaneous speech. In Proceedings of the International Conference on Spoken Language Processing (Vol. 2, pp. 831–834). Yokohama. [find](https://scholar.google.com/scholar?q=Suhm%2C+B%2E%2C+%26+Waibel%2C+A%2E+%281994%29%2E+Toward+better+language+models+for+spontaneous+speech%2E+In+Proceedings+of+the+International+Conference+on+Spoken+Language+Processing+%28Vol%2E+2%2C+pp%2E+831%E2%80%93834%29%2E+Yokohama%2E)
42. Swerts, M. (1997). Prosodic features at discourse boundaries of different strength. Journal of the Acoustical Society of America, 101, 514–521. [↗](https://doi.org/10.1121/1.418114)
43. Swerts, M., & Ostendorf, M. (1997). Prosodic and lexical indications of discourse structure in human-machine interactions. Speech Communication, 22(1), 25–41. [↗](https://doi.org/10.1016/s0167-6393(97)00011-3)
44. Taylor, P. A., & Black, A. W. (1994). Synthesizing conversational intonation from a linguistically rich input. In Proceedings of the 2nd ESCA/IEEE Workshop on Speech Synthesis (pp. 175–178). New York. [find](https://scholar.google.com/scholar?q=Taylor%2C+P%2E+A%2E%2C+%26+Black%2C+A%2E+W%2E+%281994%29%2E+Synthesizing+conversational+intonation+from+a+linguistically+rich+input%2E+In+Proceedings+of+the+2nd+ESCA%2FIEEE+Workshop+on+Speech+Synthesis+%28pp%2E+175%E2%80%93178%29%2E+New+York%2E)
45. Taylor, P. A., King, S., Isard, S. D., Wright, H., & Kowtko, J. (1997). Using intonation to constrain language models in speech recognition. In G. Kokkinakis, N. Fakotakis, & E. Dermatas (Eds.), Proceedings of the 5th European Conference on Speech Communication and Technology (Vol. 5, pp. 2763–2766). Rhodes, Greece. [find](https://scholar.google.com/scholar?q=Taylor%2C+P%2E+A%2E%2C+King%2C+S%2E%2C+Isard%2C+S%2E+D%2E%2C+Wright%2C+H%2E%2C+%26+Kowtko%2C+J%2E+%281997%29%2E+Using+intonation+to+constrain+language+models+in+speech+recognition%2E+In+G%2E+Kokkinakis%2C+N%2E+Fakotakis%2C+%26+E%2E+Dermatas+%28Eds%2E%29%2C+Proce)
46. Taylor, P., King, S., Isard, S., & Wright, H. (1998). Intonation and dialog context as constraints for speech recognition. Language and Speech, 41(3-4), 489–508. [↗](https://doi.org/10.1177/002383099804100411)
47. Terry, M., Sparks, R., & Obenchain, P. (1994). Automated query identification in English dialogue. In Proceedings of the International Conference on Spoken Language Processing (Vol. 2, pp. 891–894). Yokohama. [find](https://scholar.google.com/scholar?q=Terry%2C+M%2E%2C+Sparks%2C+R%2E%2C+%26+Obenchain%2C+P%2E+%281994%29%2E+Automated+query+identification+in+English+dialogue%2E+In+Proceedings+of+the+International+Conference+on+Spoken+Language+Processing+%28Vol%2E+2%2C+pp%2E+891%E2%80%93894%29%2E+Y)
48. Traum, D., & Heeman, P. (1996). Utterance units and grounding in spoken dialogue. In H. T. Bunnell & W. Idsardi (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 3, pp. 1884–1887). Philadelphia. [find](https://scholar.google.com/scholar?q=Traum%2C+D%2E%2C+%26+Heeman%2C+P%2E+%281996%29%2E+Utterance+units+and+grounding+in+spoken+dialogue%2E+In+H%2E+T%2E+Bunnell+%26+W%2E+Idsardi+%28Eds%2E%29%2C+Proceedings+of+the+International+Conference+on+Spoken+Language+Processing+%28Vol%2E+)
49. Vaissière, J. (1983). Language-independent prosodic features. In A. Cutler & D. R. Ladd (Eds.), Prosody: Models and Measurements (pp. 53–66). Berlin: Springer. [↗](https://doi.org/10.1007/978-3-642-69103-4_5)
50. Veilleux, N. M., & Ostendorf, M. (1993). Prosody/parse scoring and its application in ATIS. In Proceedings of the ARPA Workshop on Human Language Technology (pp. 335–340). Princeton, NJ. [find](https://scholar.google.com/scholar?q=Veilleux%2C+N%2E+M%2E%2C+%26+Ostendorf%2C+M%2E+%281993%29%2E+Prosody%2Fparse+scoring+and+its+application+in+ATIS%2E+In+Proceedings+of+the+ARPA+Workshop+on+Human+Language+Technology+%28pp%2E+335%E2%80%93340%29%2E+Princeton%2C+NJ%2E)
51. Waibel, A. (1988). Prosody and Speech Recognition. San Mateo, CA: Morgan Kaufmann. [find](https://scholar.google.com/scholar?q=Waibel%2C+A%2E+%281988%29%2E+Prosody+and+Speech+Recognition%2E+San+Mateo%2C+CA%3A+Morgan+Kaufmann%2E)
52. Warnke, V., Kompe, R., Niemann, H., & Nöth, E. (1997). Integrated dialog act segmentation and classification using prosodic features and language models. In G. Kokkinakis, N. Fakotakis, & E. Dermatas (Eds.), Proceedings of the 5th European Conference on Speech Communication and Technology (Vol. 1, pp. 207–210). Rhodes, Greece. [find](https://scholar.google.com/scholar?q=Warnke%2C+V%2E%2C+Kompe%2C+R%2E%2C+Niemann%2C+H%2E%2C+%26+No%CC%88th%2C+E%2E+%281997%29%2E+Integrated+dialog+act+segmentation+and+classification+using+prosodic+features+and+language+models%2E+In+G%2E+Kokkinakis%2C+N%2E+Fakotakis%2C+%26+E%2E+Dermatas)
53. Weber, E. (1993). Varieties of Questions in English Conversation. Amsterdam: John Benjamins. [↗](https://doi.org/10.1075/sidag.3)
54. Wightman, C. W., & Ostendorf, M. (1994). Automatic labelling of prosodic patterns. IEEE Transations on Speech and Audio Processing, 2, 469–481. [find](https://scholar.google.com/scholar?q=Wightman%2C+C%2E+W%2E%2C+%26+Ostendorf%2C+M%2E+%281994%29%2E+Automatic+labelling+of+prosodic+patterns%2E+IEEE+Transations+on+Speech+and+Audio+Processing%2C+2%2C+469%E2%80%93481%2E)
55. Woszczyna, M., & Waibel, A. (1994). Inferring linguistic structure in spoken language. In Proceedings of the International Conference on Spoken Language Processing (Vol. 2, pp. 847–850). Yokohama. [find](https://scholar.google.com/scholar?q=Woszczyna%2C+M%2E%2C+%26+Waibel%2C+A%2E+%281994%29%2E+Inferring+linguistic+structure+in+spoken+language%2E+In+Proceedings+of+the+International+Conference+on+Spoken+Language+Processing+%28Vol%2E+2%2C+pp%2E+847%E2%80%93850%29%2E+Yokohama%2E)
56. Yamaoka, T., & Iida, H. (1991). Dialogue interpretation model and its application to next utterance predication for spoken language processing. In Proceedings of the 2nd European Conference on Speech Communication and Technology (Vol. 2, pp. 849–852). Genova, Italy. [find](https://scholar.google.com/scholar?q=Yamaoka%2C+T%2E%2C+%26+Iida%2C+H%2E+%281991%29%2E+Dialogue+interpretation+model+and+its+application+to+next+utterance+predication+for+spoken+language+processing%2E+In+Proceedings+of+the+2nd+European+Conference+on+Speech+)
57. Yoshimura, T., Hayamizu, S., Ohmura, H., & Tanaka, K. (1996). Pitch pattern clustering of user utterances in human-machine dialogue. In H. T. Bunnell & W. Idsardi (Eds.), Proceedings of the International Conference on Spoken Language Processing (Vol. 2, pp. 837–840). Philadelphia. [find](https://scholar.google.com/scholar?q=Yoshimura%2C+T%2E%2C+Hayamizu%2C+S%2E%2C+Ohmura%2C+H%2E%2C+%26+Tanaka%2C+K%2E+%281996%29%2E+Pitch+pattern+clustering+of+user+utterances+in+human%2Dmachine+dialogue%2E+In+H%2E+T%2E+Bunnell+%26+W%2E+Idsardi+%28Eds%2E%29%2C+Proceedings+of+the+Internatio)

*Updated 1 November 2026*