Large vocabulary automatic speech recognition for children
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Recently, Google launched YouTube Kids, a mobile application for children, that uses a speech recognizer built specifically for recognizing children’s speech. In this paper we present techniques we explored to build such a system. We describe the use of a neural network classifier to identify matched acoustic training data, filtering data for language modeling to reduce the chance of producing offensive results. We also compare long short-term memory (LSTM) recurrent networks to convolutional, LSTM, deep neural networks (CLDNN). We found that a CLDNN acoustic model outperforms an LSTM across a variety of different conditions, but does not specifically model child speech relatively better than adult. Overall, these findings allow us to build a successful, state-of-the-art large vocabulary speech recognizer for both children and adults.
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
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
Self-citationConvolutional, 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
Self-citationLow-rank matrix factorization for Deep Neural Network training with high-dimensional output targets
Sainath, T. N., Kingsbury, B., Sindhwani, V., Arisoy, E., & Ramabhadran, B. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638949 · Cited by 593 · cited 1×
“To reduce the network size, the softmax layer is factored into two with an intermediate 512-node linear low-rank layer [27].”
MethodSelf-citation
Cited by
Shahin, M., Zafar, U., & Ahmed, B. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2959393 · Cited by 62
“Still,themosteffective waytoimprovechildacousticmodelistouselargeamountsof childtrainingdata[81].”
MethodHow Might We Create Better Benchmarks for Speech Recognition?
Aksënova, A., van Esch, D., Flynn, J., & Golik, P. (2021) · Proceedings of the 1st Workshop on Benchmarking: Past, Present and Future · doi:10.18653/v1/2021.bppf-1.4 · Cited by 25
“…differences, e.g. double-negatives • voice quality differences, e.g. pitch differences, which are correlated with parameters such as gender and age (Liao et al., 2015) Fortunately, several data sets already exist with relevant demographic tags for many utterances, e.g. Mozilla Common Voice (Ardila…”
BackgroundInfluentialReproducible Speech Research With the Artificial Intelligence–Ready PERCEPT Corpora
Benway, N. R., Preston, J. L., Hitchcock, E., Rose, Y., Salekin, A., Liang, W., & McAllister, T. (2023) · Journal of Speech, Language, and Hearing Research · doi:10.1044/2023_jslhr-22-00343 · Cited by 12
Metadata
- Authors
- Liao, H., Pundak, G., Siohan, O., Carroll, M. K., Coccaro, N., Jiang, Q.-M., Sainath, T. N., Senior, A., Beaufays, F., & Bacchiani, M.
- Venue
- Interspeech 2015
- Publisher
- ISCA
- Published
- 2015-09-06
- Pages
- 1611-1615
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2295983515
- Cited by
- 97
- References
- 3
- FWCI
- 6.63
- 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
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.