Exploring multidimensional lstms for large vocabulary ASR
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Long short-term memory (LSTM) recurrent neural networks (RNNs) have recently shown significant performance improvements over deep feed-forward neural networks. A key aspect of these models is the use of time recurrence, combined with a gating architecture that allows them to track the long-term dynamics of speech. Inspired by human spectrogram reading, we recently proposed the frequency LSTM (F-LSTM) that performs 1-D recurrence over the frequency axis and then performs 1-D recurrence over the time axis. In this study, we further improve the acoustic model by proposing a 2-D, time-frequency (TF) LSTM. The TF-LSTM jointly scans the input over the time and frequency axes to model spectro-temporal warping, and then uses the output activations as the input to a time LSTM (T-LSTM). The joint time-frequency modeling better normalizes the features for the upper layer T-LSTMs. Evaluated on a 375-hour short message dictation task, the proposed TF-LSTM obtained a 3.4% relative WER reduction over the best T-LSTM. The invariance property achieved by joint time-frequency analysis is demonstrated on a mismatched test set, where the TF-LSTM achieves a 14.2% relative WER reduction over the best T-LSTM.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 9×
“This problem is well handled in the LSTM-RNNs through the use of the following four components: Memory units: these store the temporal state of the network; Input gates: these modulate the input activations into the cells; Output gates: these modulate the output activations of the cells ; Forget gates: these adaptivel…”
BackgroundInfluentialGraves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
Long short-term memory recurrent neural network architectures for large scale acoustic modeling
Sak, H., Senior, A., & Beaufays, F. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-80 · Cited by 2,973
Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks
Sainath, T. N., Vinyals, O., Senior, A., & Sak, H. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178838 · Cited by 1,678
Recent advances in deep learning for speech research at Microsoft
Deng, L., Li, J., Huang, J.-T., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., Williams, J., et al. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639345 · Cited by 801 · cited 1×
“Recently, significant progress has been made in automatic speech recognition (ASR) thanks to the application of deep neural networks (DNNs) [1][2][3][4][5][6].”
BackgroundSelf-citationMulti-dimensional Recurrent Neural Networks
Graves, A., Fernández, S., & Schmidhuber, J. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-74690-4_56 · Cited by 303 · cited 6×
“We will also implement the multidimensional LSTM with multiple forget gates [17][18] and compare with our proposed method.”
BackgroundMethodInfluentialLSTM time and frequency recurrence for automatic speech recognition
Li, J., Mohamed, A., Zweig, G., & Gong, Y. (2015) · 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2015.7404793 · Cited by 119
Self-citation
Cited by
A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
Yu, Y., Si, X., Hu, C., & Zhang, J. (2019) · Neural Computation · doi:10.1162/neco_a_01199 · Cited by 5,591
Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition
Dong, L., Xu, S., & Xu, B. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8462506 · Cited by 1,100
Deep Learning for Audio Signal Processing
Purwins, H., Li, B., Virtanen, T., Schluter, J., Chang, S.-Y., & Sainath, T. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2908700 · Cited by 855
Speech Emotion Recognition with Dual-Sequence LSTM Architecture
Wang, J., Xue, M., Culhane, R., Diao, E., Ding, J., & Tarokh, V. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054629 · Cited by 162
“As the field of Automatic Speech Recognition (ASR) rapidly matures, people are beginning to realize that the information conveyed in speech goes beyond its textual content.”
BackgroundInfluentialLSTM time and frequency recurrence for automatic speech recognition
Li, J., Mohamed, A., Zweig, G., & Gong, Y. (2015) · 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2015.7404793 · Cited by 119
Self-citation
Metadata
- Authors
- Li, J., Mohamed, A., Zweig, G., & Gong, Y.
- Venue
- 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2016-03
- Pages
- 4940-4944
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2396144419
- Cited by
- 56
- References
- 7
- FWCI
- 5.99
- Type
- conference paper
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exploring multidimensional lstms for large vocabulary ASR. https://app.cochat.ai/papers/10.1109/icassp.2016.7472617
- The paper
- Li, J., Mohamed, A., Zweig, G., & Gong, Y. (2016). Exploring multidimensional lstms for large vocabulary ASR. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2016.7472617
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.