Convolutional Neural Networks for Distant Speech Recognition
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
We investigate convolutional neural networks (CNNs) for large vocabulary distant speech recognition, trained using speech recorded from a single distant microphone (SDM) and multiple distant microphones (MDM). In the MDM case we explore a beamformed signal input representation compared with the direct use of multiple acoustic channels as a parallel input to the CNN. We have explored different weight sharing approaches, and propose a channel-wise convolution with two-way pooling. Our experiments, using the AMI meeting corpus, found that CNNs improve the word error rate (WER) by 6.5% relative compared to conventional deep neural network (DNN) models and 15.7% over a discriminatively trained Gaussian mixture model (GMM) baseline. For cross-channel CNN training, the WER improves by 3.5% relative over the comparable DNN structure. Compared with the best beamformed GMM system, cross-channel convolution reduces the WER by 9.7% relative, and matches the accuracy of a beamformed DNN.
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
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Kaldi Speech Recognition Toolkit
Povey, D. (2024) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.57702/jb3fvbn9 · Cited by 4,609
Convolutional networks for images, speech, and time series
LeCun, Y., & Bengio, Y. (1998) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.5555/303568.303704 · Cited by 4,231
The Handbook of brain theory and neural networks
(1996) · Choice Reviews Online · doi:10.5860/choice.33-4484 · Cited by 3,870
Hierarchical models of object recognition in cortex
Riesenhuber, M., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/14819 · Cited by 3,309 · cited 1×
“…+ bl), for 2 l < L (5) a L = W L h L 1 + b L, P (s|ot) = exp{aL(s)}P s0 exp{aL(s0)} , (6) where hl is the input to the (l+1)-th layer, with h1 = p; Wl is the matrix of connection weights and bl is the additive bias vector for the l-th layer; (·) is a sigmoid nonlinearlity that operates…”
BackgroundContext-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011 · cited 1×
“tended the state-of-the-art in acoustic modelling for automatic speech recognition (ASR), using both hybrid configurations [6]–[11] in which the neural network is used to estimate hidden Markov model (HMM) output probabilities and posteriorgram configurations [12]–[15] in which the neural network provides discriminati…”
MethodPhoneme recognition using time-delay neural networks
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/29.21701 · Cited by 2,643
An empirical study of smoothing techniques for language modeling
Chen, S. F., & Goodman, J. (1999) · Computer Speech & Language · doi:10.1006/csla.1999.0128 · Cited by 2,066
Research works printed but not linked: 2
- abdel-hamid, 2013, Exploring convolutional neural network structures and optimisation techniques for speech recognition, Proc INTERSPEECH
- cieri, 2003, From switchboard to fisher: Telephone collection protocols, their uses and yields, Proc EUROSPEECH, 10.21437/Eurospeech.2003-466 · doi:10.21437/eurospeech.2003-466
Cited by
A survey on deep learning for big data
Zhang, Q., Yang, L. T., Chen, Z., & Li, P. (2018) · Information Fusion · doi:10.1016/j.inffus.2017.10.006 · Cited by 1,226
Human activity recognition with smartphone sensors using deep learning neural networks
Ronao, C. A., & Cho, S.-B. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.04.032 · Cited by 1,215
Speech Recognition Using Deep Neural Networks: A Systematic Review
Nassif, A. B., Shahin, I., Attili, I., Azzeh, M., & Shaalan, K. (2019) · IEEE Access · doi:10.1109/access.2019.2896880 · Cited by 1,152
Deep learning approach for active classification of electrocardiogram signals
Rahhal, M. M. A., Bazi, Y., AlHichri, H., Alajlan, N., Melgani, F., & Yager, R. R. (2016) · Information Sciences · doi:10.1016/j.ins.2016.01.082 · Cited by 627
Adavanne, S., Politis, A., Nikunen, J., & Virtanen, T. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2018.2885636 · Cited by 534
A deep learning approach to detection of splicing and copy-move forgeries in images
Rao, Y., & Ni, J. (2016) · 2016 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2016.7823911 · Cited by 516
Neural network based spectral mask estimation for acoustic beamforming
Heymann, J., Drude, L., & Haeb-Umbach, R. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7471664 · Cited by 480
Very Deep Convolutional Neural Networks for Noise Robust Speech Recognition
Qian, Y., Bi, M., Tan, T., & Yu, K. (2016) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2016.2602884 · Cited by 343
Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments
Zhang, Z., Geiger, J., Pohjalainen, J., Mousa, A. E.-D., Jin, W., & Schuller, B. (2018) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3178115 · Cited by 313
A novel deep learning-based method for damage identification of smart building structures
Yu, Y., Wang, C., Gu, X., & Li, J. (2019) · Structural Health Monitoring · doi:10.1177/1475921718804132 · Cited by 311
Deep Learning Approach for Car Detection in UAV Imagery
Ammour, N., Alhichri, H., Bazi, Y., Benjdira, B., Alajlan, N., & Zuair, M. (2017) · Remote Sensing · doi:10.3390/rs9040312 · Cited by 296
Highway long short-term memory RNNS for distant speech recognition
Zhang, Y., Chen, G., Yu, D., Yao, K., Khudanpur, S., & Glass, J. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472780 · Cited by 290
Analysis of CNN-based speech recognition system using raw speech as input
Palaz, D., Magimai-Doss, M., & Collobert, R. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-3 · Cited by 288
Prediction of human protein subcellular localization using deep learning
Wei, L., Ding, Y., Su, R., Tang, J., & Zou, Q. (2018) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2017.08.009 · Cited by 216
Palaz, D., Magimai-Doss, M., & Collobert, R. (2019) · Speech Communication · doi:10.1016/j.specom.2019.01.004 · Cited by 168
Automatic Speech Recognition Errors Detection and Correction: A Review
Errattahi, R., El Hannani, A., & Ouahmane, H. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.03.005 · Cited by 155
“Nevertheless LVCSR systems are not yet robust with error rates of up to 50% under certain conditions [1],[2].”
BackgroundArtificial intelligence moving serious gaming: Presenting reusable game AI components
Westera, W., Prada, R., Mascarenhas, S., Santos, P. A., Dias, J., Guimarães, M., Georgiadis, K., Nyamsuren, E., Bahreini, K., Yumak, Z., et al. (2020) · Education and Information Technologies · doi:10.1007/s10639-019-09968-2 · Cited by 136
Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation
Swietojanski, P., Li, J., & Renals, S. (2016) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2016.2560534 · Cited by 133
“For AMI, we also evaluate the effectiveness of LHUC and SAT-LHUC on AMs that utilise convolutional layers [8], [62], [63], where the CNN networks were trained as described in [64] but with 300 convolutional filters.”
MethodSelf-citationNew Era for Robust Speech Recognition
(2017) · doi:10.1007/978-3-319-64680-0 · Cited by 48
Metadata
- Authors
- Swietojanski, P., Ghoshal, A., & Renals, S.
- Venue
- IEEE Signal Processing Letters
- Published
- 2014-09
- Volume
- 21
- Issue
- 9
- Pages
- 1120-1124
- ISSN
- 1070-9908 (ISSN-L)
- 1558-2361
- OpenAlex
- W2103088716
- Cited by
- 253
- References
- 43
- FWCI
- 25.42
- Type
- journal article
- Language
- en
- Open access
- green
- Funders
- Engineering and Physical Sciences Research Council (EP/I031022/1)
- European Commission (287872)
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.