The DOI matches its Crossref record.
Densely Connected Networks for Conversational Speech Recognition
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cited by
Sorted by citations
Deep learning for human affect recognition: Insights and new developments
Rouast, P. V., Adam, M. T. P., & Chiong, R. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2018.2890471 · Cited by 243
Villalba, J., Chen, N., Snyder, D., Garcia-Romero, D., McCree, A. V., Sell, G., Borgstrom, J., Garcia, L. P., Richardson, F. S., Dehak, R., et al. (2019) · Computer Speech & Language · doi:10.1016/j.csl.2019.101026 · Cited by 129
Earnings-21: A Practical Benchmark for ASR in the Wild
Rio, M. D., Delworth, N., Westerman, R., Huang, M., Bhandari, N., Palakapilly, J., McNamara, Q., Dong, J., Żelasko, P., & Jetté, M. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1915 · Cited by 46
“Whereas the best reported word error rate (WER) results on LibriSpeech (around 1.4% [11]) or Switchboard (around 5% [12]) are encouraging, in reality, most commercially available systems are much closer to 15-20% [10] when transcribing user-provided recordings, making ASR a problem that is far from…”
BackgroundInfluentialASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition
Pan, J. S., Shapiro, J., Wohlwend, J., Han, K. J., Lei, T., & Ma, T. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2947 · Cited by 30
“It consists of a pyramidal structure of bLSTMs for the encoder with contentaware attention.”
BackgroundInfluentialSelf-citationHuang, L., Cheng, G., Zhang, P., Yang, Y., Xu, S., & Sun, J. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023163 · Cited by 6
ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech RecognitionPreprint
Pan, J. S., Shapiro, J., Wohlwend, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.10469 · Cited by 3
“It consists of a pyramidal structure of bLSTMs for the encoder with contentaware attention.”
BackgroundInfluentialSelf-citation
Metadata
- Authors
- Han, K., Chandrashekaran, A., Kim, J., & Lane, I.
- ORCID
- Kim, Jungsuk
- Venue
- Interspeech 2018
- Publisher
- ISCA
- Published
- 2018-09-02
- Pages
- 796-800
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2889129873
- Cited by
- 5
- References
- 0
- Citations by year
- 2021: 1 · 2020: 1 · 2019: 3
- FWCI
- 0.51
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- conversational speech recognition, densely connected network, neural network architecture, speech recognition
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
