Super-human multi-talker speech recognition: A graphical modeling approach
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
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
An Algorithm for Vector Quantizer Design
Linde, Y., Buzo, A., & Gray, R. (1980) · IEEE Transactions on Communications · doi:10.1109/tcom.1980.1094577 · Cited by 7,201 · cited 2×
“In Hershey et al. (2006) exact inference of the state sequences (temporal inference), was done using factorial HMM 2-D Viterbi search, for the grammar dynamics model.”
MethodFactor graphs and the sum-product algorithm
Kschischang, F. R., Frey, B. J., & Loeliger, H.-A. (2001) · IEEE Transactions on Information Theory · doi:10.1109/18.910572 · Cited by 6,486 · cited 1×
“Using the max-product belief propagation method, Kschischang et al., 2001, temporal inference can be accomplished with complexity OðTND 2 v Þ, scaling linearly in the number of speakers.”
MethodMaximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
Gauvain, J.-L., & Lee, C.-H. (1994) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.279278 · Cited by 2,108 · cited 1×
“We employed MAP training Gauvain and Lee, 1994 to train a speaker-dependent model for each of the 34 speakers.”
Method2007 IEEE International Conference on Acoustics, Speech, and Signal Processing
(2007) · 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 · doi:10.1109/icassp.2007.366148 · Cited by 1,520
Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models
Hershey, J. R., & Olsen, P. A. (2007) · 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 · doi:10.1109/icassp.2007.366913 · Cited by 1,189 · cited 1×
“Under this model the d Gaussians are optimized by minimizing the KL-divergence D s ð P s a pðs a Þpðx a js a Þjj P s a pðs a Þ^ pðx a js a ÞÞ, and likewise for s b , using the variational approximation of Hershey and Olsen (2007).”
MethodSelf-citationFactorial Hidden Markov Models
Ghahramani, Z., & Jordan, M. I. (1997) · Machine Learning · doi:10.1023/a:1007425814087 · Cited by 1,157 · cited 1×
“The forward–backward algorithm for a factorial HMM with N source models requires only OðTND N þ1 Þ rather than the OðTD 2N Þ required for a naive implementation (Ghahramani and Jordan, 1995).”
MethodAn audio-visual corpus for speech perception and automatic speech recognition
Cooke, M., Barker, J., Cunningham, S., & Shao, X. (2006) · The Journal of the Acoustical Society of America · doi:10.1121/1.2229005 · Cited by 1,144
On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs
Weiss, Y., & Freeman, W. T. (2001) · IEEE Transactions on Information Theory · doi:10.1109/18.910585 · Cited by 581 · cited 1×
“If the algorithm does converge (meaning that all conditional estimates ^ x Cni ðx i Þ are consistent), the MAP estimate is provably optimal over all tree and single-loop sub-structures of the probability model (Weiss and Freeman, 2001).”
Hidden Markov model decomposition of speech and noise
Varga, A. P., & Moore, R. K. (2002) · International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1990.115970 · Cited by 467 · cited 1×
“In Varga and Moore (1990), such a model was used to compute state likelihoods and find the optimal state sequence.”
MethodRobust continuous speech recognition using parallel model combination
Gales, M., & Young, S. J. (1996) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.536929 · Cited by 439
Cited by
Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation
Luo, Y., & Mesgarani, N. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2915167 · Cited by 2,042
Deep clustering: Discriminative embeddings for segmentation and separation
Hershey, J. R., Chen, Z., Le Roux, J., & Watanabe, S. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7471631 · Cited by 1,354
Self-citationOn Training Targets for Supervised Speech Separation
Wang, Y., Narayanan, A., & Wang, D. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2352935 · Cited by 1,067
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks
Erdogan, H., Hershey, J. R., Watanabe, S., & Le Roux, J. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178061 · Cited by 646
Self-citationAchieving Human Parity in Conversational Speech Recognition
Xiong, W., Droppo, J., Huang, X., Seide, F. T. B., Seltzer, M., Stolcke, A., Yu, D., & Zweig, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.05256 · Cited by 451
The PASCAL CHiME speech separation and recognition challenge
Barker, J., Vincent, E., Ma, N., Christensen, H., & Green, P. (2013) · Computer Speech & Language · doi:10.1016/j.csl.2012.10.004 · Cited by 213
“The challenge was remarkable in that the best-performing system was able to produce super-human performance (Hershey et al., 2010).”
Background
Metadata
- Authors
- Hershey, J. R., Rennie, S. J., Olsen, P. A., & Kristjansson, T. T.
- Venue
- Computer Speech & Language
- Publisher
- Elsevier BV
- Published
- 2010-01
- Volume
- 24
- Issue
- 1
- Pages
- 45-66
- ISSN
- 0885-2308 (ISSN-L)
- OpenAlex
- W2079362249
- Cited by
- 166
- References
- 19
- FWCI
- 16.26
- Type
- journal article
- Language
- en
- Open access
- closed
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.