Disfluency Detection Using a Bidirectional LSTM
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
We introduce a new approach for disfluency detection using a Bidirectional Long-Short Term Memory neural network (BLSTM). In addition to the word sequence, the model takes as input pattern match features that were developed to reduce sensitivity to vocabulary size in training, which lead to improved performance over the word sequence alone. The BLSTM takes advantage of explicit repair states in addition to the standard reparandum states. The final output leverages integer linear programming to incorporate constraints of disfluency structure. In experiments on the Switchboard corpus, the model achieves state-of-the-art performance for both the standard disfluency detection task and the correction detection task. Analysis shows that the model has better detection of non-repetition disfluencies, which tend to be much harder to detect.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
SWITCHBOARD: telephone speech corpus for research and development
Godfrey, J. J., Holliman, E. C., & McDaniel, J. (1992) · [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1992.225858 · Cited by 2,134 · cited 1×
“We assess the proposed BLSTM model for disfluency detection in experiments on the Switchboard corpus of conversational speech [26], using the standard division of the disfluencyannotated subset into training, development and test sets.”
MethodLSTM neural networks for language modeling
Sundermeyer, M., Schlüter, R., & Ney, H. (2012) · Interspeech 2012 · doi:10.21437/interspeech.2012-65 · Cited by 1,963 · cited 1×
“We use LSTM RNNs for the task of disfluency detection, since LSTMs achieve good performance in a variety of NLP sequence modeling tasks [20, 21, 22].”
Method
Cited by
Automated Analysis and Prediction of Job Interview Performance
Naim, I., Tanveer, M. I., Gildea, D., & Hoque, M. E. (2018) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2016.2614299 · Cited by 161
FluentNet: End-to-End Detection of Stuttered Speech Disfluencies With Deep Learning
Kourkounakis, T., Hajavi, A., & Etemad, A. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3110146 · Cited by 109
Kourkounakis, T., Hajavi, A., & Etemad, A. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053893 · Cited by 87
Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering
Gupta, A., Xu, J., Upadhyay, S., Yang, D., & Faruqui, M. (2021) · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · doi:10.18653/v1/2021.findings-acl.293 · Cited by 22
Neural Constituency Parsing of Speech Transcripts
Jamshid Lou, P., Wang, Y., & Johnson, M. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1282 · Cited by 22
“Previous work shows that LSTMs and CNNs operating on words alone are poor at disfluency detection (Zayats et al., 2016; Wang et al., 2016; Jamshid Lou et al., 2018).”
Background
Metadata
- Authors
- Zayats, V., Ostendorf, M., & Hajishirzi, H.
- Venue
- Interspeech 2016
- Publisher
- ISCA
- Published
- 2016-09-08
- Pages
- 2523-2527
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2338935876
- Cited by
- 106
- References
- 3
- FWCI
- 4.90
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.