The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Learning a better representation of speech soundwaves using restricted boltzmann machines
Abstract
State of the art speech recognition systems rely on preprocessed speech features such as Mel cepstrum or linear predictive coding coefficients that collapse high dimensional speech sound waves into low dimensional encodings. While these have been successfully applied in speech recognition systems, such low dimensional encodings may lose some relevant information and express other information in a way that makes it difficult to use for discrimination. Higher dimensional encodings could both improve performance in recognition tasks, and also be applied to speech synthesis by better modeling the statistical structure of the sound waves. In this paper we present a novel approach for modeling speech sound waves using a Restricted Boltzmann machine (RBM) with a novel type of hidden variable and we report initial results demonstrating phoneme recognition performance better than the current state-of-the-art for methods based on Mel cepstrum coefficients.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
(2010) · International Conference on Machine Learning · Cited by 13,995
Self-citationAn Information-Maximization Approach to Blind Separation and Blind Deconvolution
Bell, A. J., & Sejnowski, T. J. (1995) · Neural Computation · doi:10.1162/neco.1995.7.6.1129 · Cited by 8,986
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 3×
“a weight parameter, wij ∈ W is as follows [6]:”
BackgroundMethodSelf-citationA Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852
Self-citationInformation processing in dynamical systems: foundations of harmony theory
Smolensky, P. (1986) · The MIT Press eBooks · Cited by 1,673
Advances in Neural Information Processing Systems 19 (NIPS 2006)
Simonotto, E., Whalley, H. C., Lawrie, S. M., Murray, L. M., McGonigle, D. J., & Storkey, A. (2006) · Cited by 1,651
(2009) · neural information processing systems · Cited by 962
Efficient coding of natural sounds
Lewicki, M. S. (2002) · Nature Neuroscience · doi:10.1038/nn831 · Cited by 697
An application of recurrent nets to phone probability estimation
Robinson, A. J. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279192 · Cited by 441
Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine
Dahl, G. E., Ranzato, M., Mohamed, A., & Hinton, G. E. (2010) · Cited by 266
Self-citation
Flagged first, then by citations
Research works printed but not linked: 1
- Mohamed, Deep belief networks for phone recognition
Cited by
Sorted by citations
Items 201–231 of 231
Tomashenko, N. (2017) · theses.fr (ABES) · doi:10.70675/9321e219z572az4822z8fffz3a7e47751802 · Cited by 1
The automatic and unconstrained segmentation of speech into subword units
Vuuren, V., & Zyl, V. (2014)
Nguyen, M. C. (2014) · DR-NTU (Nanyang Technological University)
Unsupervised Filterbank Learning for Speech-based Access System for Agricultural Commodity
Sailor, H. B., Patil, H. A., & Rajpal, A. (2017) · International Conference on Advances in Pattern Recognition · doi:10.1109/icapr.2017.8593040
Avaliação da Qualidade da Voz em Serviços de Comunicação usando Deep Learning
Gouveia, D. J. D. S., Rosa, R. L., & Rodríguez, D. Z. (2018) · doi:10.5753/sbrc.2018.2415
Auditory Representation Learning
Sailor, H. B. (2018)
Convergence of Markovian stochastic approximation for Markov random fields with hidden variables
Qi, A., Yang, L., & Huang, C. (2019) · Stochastics and Dynamics · doi:10.1142/s021949372050029x
A Long Short-term Memory Neural Network for Improved Twins' Voice Differentiation
Sabatier, S. B.-R. (2018) · doi:10.33915/etd.6551
“This trend is in line with [85] who performed language identification with an LSTM and i-vector and found the LSTM outperformed the other by 26% with three seconds worth of speech data and accuracy over 50% with 0.”
MethodAshley, D. R., Kanervisto, A., & Bennett, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00698
Research of Attention-LSTM Model for Baby Cry Detection Robot
Jian, T., Peng, Y., Peng, W., & Zhou, Y. (2021) · Proceedings of International Conference on Artificial Life and Robotics · doi:10.5954/icarob.2021.os3-2
Mak, M., & Chien, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108552332.005 · Cited by 1
Speech Representations and Phoneme Classification for Preserving the Endangered Language of LadinPreprint
Durante, Z., Mathur, L., Ye, E., Zhao, S., Ramdas, T., & Iskarous, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.12531
“This approach was informed by prior research using Restricted Boltzmann Machines to represent raw speech [28].”
MethodLearning Deep Representation of The Emotion Speech Signal
Duan, J., Zheng, S., & Zhao, J. (2021) · EAI International Conference on Green Energy and Networking (GreeNets) · doi:10.4108/eai.6-6-2021.2307539
“Experiments on the TIMIT phoneme recognition task achieved state-of-the-art results at the time [22].”
MethodMak, M., & Chien, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108552332.001
Mak, M., & Chien, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108552332.010
Mak, M., & Chien, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108552332.009
Mak, M., & Chien, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108552332.002
Dimension Reduction and Data Augmentation
Mak, M., & Chien, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108552332.008
Mak, M., & Chien, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108552332.011
Audio-based cold-start in music recommendation systems
Borges, R. (2022) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.45.2022.tde-14102022-124655
ASFNet: Audio Spectrogram Fourier Network for Efficient Medical Sound Event DetectionPreprint
HASSAN, K. M. N., & Haque, M. A. (2023) · doi:10.36227/techrxiv.23732205.v1
Neural networks and deep learning: part I
Theodoridis, S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-329238-5.00024-x
Behavioral Computing for Human Factor Security and Safety in Infrastructure Construction
Wang, C. (2025) · Springer eBooks · doi:10.1007/978-981-96-5194-8_10
Gamma-von-Mises restricted Boltzmann machine and its application to audio modeling
Nakashika, T., & Yatabe, K. (2025) · Nippon Onkyo Gakkaishi/Acoustical science and technology/Nihon Onkyo Gakkaishi · doi:10.1250/ast.e24.95
A Noise-Robust End-to-End Framework for Amharic Speech Recognition
Ejigu, Y. A., Asfaw, T. T., Tadesse, S. A., Tegegne, A. Y., & Chekole, A. K. (2025) · International Conference on Information and Communication Technology for Development for Africa (ICT4DA) · doi:10.1109/ict4da67218.2025.11282733
Breaking Barriers in Amharic Speech Recognition: A Scalable End-to-End Approach
Asfaw, T. T., & Ejigu, Y. A. (2026) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-032-04203-3_1
Short time-scale efficient coding of speech
Deloche, F. (2019) · theses.fr (ABES) · doi:10.70675/438cec3czcd2dz444bz85aaza0ba4fc6fd89
Learning representations of speech from the raw waveform
Zeghidour, N. (2019) · theses.fr (ABES) · doi:10.70675/2d69ced4z8cd6z40f9z996dzacc325ed994f · Cited by 2
“To the best of our knowledge, the first attempt at training a deep neural network from the raw waveform for speech recognition is [Jaitly and Hinton, 2011] in which Jaitly and Hinton train a Restricted Boltzmann machine (RBM) as a generative model of small speech segments.”
BackgroundSvendsen, L. M., Shanbhag, V. V., & Schlanbusch, R. (2026) · Sensors · doi:10.3390/s26092856
“In parallel, following the emergence of deep neural networks, audio classification has transitioned from models based on manually engineered or derived features [9,10] to end-to-end models that directly map audio spectrograms to the corresponding labels [11–14].”
InfluentialMultimodal Eye Tracking Using Camera Vision and Electrooculography for Assistive Mobility Control
Rashid, A., Cheema, M. O., Usman, H. M., Din, Z. M. U., & Waris, A. (2026) · International Conference on Robotics and Automation in Industry (ICRAI) · doi:10.1109/icrai70912.2026.11551940
“Similarly, Minsang Seo et al. developed a control system of a trans-radial prosthetic hand based on surface EMG signals [12].”
Metadata
- Authors
- Jaitly, N., & Hinton, G.
- Affiliations
- University of Toronto (CA)
- Venue
- 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2011-05
- Pages
- 5884-5887
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2132037657
- Cited by
- 231
- References
- 19
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 3 · 2023: 11 · 2022: 8 · 2021: 24 · 2020: 34 · 2019: 29 · 2018: 21 · 2017: 16 · 2016: 22 · 2015: 16 · 2014: 17 · 2013: 9 · 2012: 5
- FWCI
- 9.01
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
- Keywords
- restricted Boltzmann machine, phoneme recognition, hidden variables, speech feature extraction, speech synthesis
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
