---
title: "The Development of Spectral and Temporal — Tan 2026"
description: "The paper asks whether a learner exposed only to speech develops two separable kinds of knowledge: what a sound is (spectral or phoneme-category…"
authors: ["Frank Lihui Tan", "Youngah Do"]
year: 2026
venue: "Proceedings of the Society for Computation in Linguistics 2026"
source: "https://aclanthology.org/2026.scil-main.11/"
doi: "10.18653/v1/2026.scil-main.11"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tan-2026-development-spectral-temporal-encodings-speech/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tan-2026-development-spectral-temporal-encodings-speech/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/10/) / The Development of Spectral and Temporal Encodings in Speech Sounds

# The Development of Spectral and Temporal Encodings in Speech Sounds

**Authors:** Frank Lihui Tan, [Youngah Do](https://md.research.elamur.ai/free/en/authors/youngah-do/) · **Year:** 2026 · **Venue:** Proceedings of the Society for Computation in Linguistics 2026 · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.scil-main.11/) · [PDF](https://aclanthology.org/2026.scil-main.11.pdf) · [DOI 10.18653/v1/2026.scil-main.11](https://doi.org/10.18653/v1/2026.scil-main.11) · [OpenAlex](https://openalex.org/W7166879167)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
The paper asks whether a learner exposed only to speech develops two separable kinds of knowledge: what a sound is (spectral or phoneme-category information) and where it occurs in a sequence (relative position). It also asks how both develop over time. Neuroscience has documented spectral encoding in auditory cortex, but no study has found dedicated positional coding or compared how the two emerge. The authors trained an unsupervised LSTM autoencoder with scaled dot-product cross-attention to reconstruct Mel-spectrograms. The inputs were artificial vowel–consonant–vowel tokens built from single-speaker LibriSpeech segments. At every epoch, they ran layer-wise ABX tests that contrasted phoneme categories and the same vowel in first versus third position. Different components came to favour either category or position, while higher-level representations combined both. These specializations were absent at the start. Layers first encoded both kinds of information in an exploratory phase, then suppressed the dimension they did not specialize in. The work offers a computational hypothesis for neuroscience and acquisition research on separable positional encoding in speech.

## Key points
- Data: the LibriSpeech "train-clean-100" subset (100 h, 16 kHz, 251 speakers), with Montreal Forced Aligner alignments from Lugosch et al. (2019). Stimuli were concatenated V-S-V and V-SH-V tokens using six vowels (AA, AE, IY, UW, AY, EY), balanced at 25,238 tokens per template.
- Model and training: the encoder uses FC and bidirectional LSTM layers, followed by cross-attention and a decoder. It was trained with Adam (learning rate 0.0005) for 100 epochs, with 5 independent runs. Epoch 0, the untrained state, was also evaluated.
- Evaluation: z-scored representations from each layer were compared against a 96-dimensional input Mel-spectrogram baseline. Each ABX test was repeated 6 times with 20 samples per class. A same-phoneme, same-position control was included.
- Main finding: layers became specialized for either spectral or positional information, and this specialization emerged dynamically during learning rather than being built in. The trajectory included "de-learning" of contrasts outside a layer's specialty.
- Limitations: only an LSTM was tested, with no Transformer or CNN comparison. The model is not claimed to mirror infant cortex. Data and scripts are shared on OSF.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{tan2026development,
  title = {{The Development of Spectral and Temporal Encodings in Speech Sounds}},
  author = {Tan, Frank Lihui and Do, Youngah},
  booktitle = {Proceedings of the Society for Computation in Linguistics 2026},
  year = {2026},
  doi = {10.18653/v1/2026.scil-main.11},
  url = {https://doi.org/10.18653/v1/2026.scil-main.11}
}
```

- [← previous The Construction of a Mixe Variant Parallel Corpus](https://md.research.elamur.ai/free/en/papers/ruiz-2026-construction-mixe-variant-parallel-corpus/)
- [next → The Effectiveness of Digital Applications in Teaching Grammar to Non-Arabic Speakers: Talkpal as an Example](https://md.research.elamur.ai/free/en/papers/malmous-2026-effectiveness-digital-applications-teaching-grammar/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/10/)

## References

57 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. arXiv preprint. Version Number: 3. [find](https://scholar.google.com/scholar?q=Alexei+Baevski%2C+Henry+Zhou%2C+Abdelrahman+Mohamed%2C+and+Michael+Auli%2E+2020%2E+wav2vec+2%2E0%3A+A+Framework+for+Self%2DSupervised+Learning+of+Speech+Representations%2E+arXiv+preprint%2E+Version+Number%3A+3%2E) [our card](https://md.research.elamur.ai/free/en/papers/baevski-2020-wav2vec-2-0-framework-self/)
2. Gašper Beguš. 2020. Generative Adversarial Phonology: Modeling Unsupervised Phonetic and Phonological Learning With Neural Networks. Frontiers in Artificial Intelligence, 3:44. [find](https://scholar.google.com/scholar?q=Ga%C5%A1per+Begu%C5%A1%2E+2020%2E+Generative+Adversarial+Phonology%3A+Modeling+Unsupervised+Phonetic+and+Phonological+Learning+With+Neural+Networks%2E+Frontiers+in+Artificial+Intelligence%2C+3%3A44%2E)
3. Silvia Benavides-Varela and Jacques Mehler. 2015. Verbal Positional Memory in 7-Month-Olds. Child Development, 86(1):209–223. [find](https://scholar.google.com/scholar?q=Silvia+Benavides%2DVarela+and+Jacques+Mehler%2E+2015%2E+Verbal+Positional+Memory+in+7%2DMonth%2DOlds%2E+Child+Development%2C+86%281%29%3A209%E2%80%93223%2E)
4. Nicholas Furl, Sukhbinder Kumar, Kai Alter, Simon Durrant, John Shawe-Taylor, and Timothy D. Griffiths. 2011. Neural prediction of higher-order auditory sequence statistics. NeuroImage, 54(3):2267– 2277. [find](https://scholar.google.com/scholar?q=Nicholas+Furl%2C+Sukhbinder+Kumar%2C+Kai+Alter%2C+Simon+Durrant%2C+John+Shawe%2DTaylor%2C+and+Timothy+D%2E+Griffiths%2E+2011%2E+Neural+prediction+of+higher%2Dorder+auditory+sequence+statistics%2E+NeuroImage%2C+54%283%29%3A2267%E2%80%93+22)
5. LouAnn Gerken. 2006. Decisions, decisions: infant language learning when multiple generalizations are possible. Cognition, 98(3):B67–74. [find](https://scholar.google.com/scholar?q=LouAnn+Gerken%2E+2006%2E+Decisions%2C+decisions%3A+infant+language+learning+when+multiple+generalizations+are+possible%2E+Cognition%2C+98%283%29%3AB67%E2%80%9374%2E)
6. F.A. Gers and E. Schmidhuber. 2001. LSTM recurrent networks learn simple context-free and context-sensitive languages. IEEE Transactions on Neural Networks, 12(6):1333–1340. [find](https://scholar.google.com/scholar?q=F%2EA%2E+Gers+and+E%2E+Schmidhuber%2E+2001%2E+LSTM+recurrent+networks+learn+simple+context%2Dfree+and+context%2Dsensitive+languages%2E+IEEE+Transactions+on+Neural+Networks%2C+12%286%29%3A1333%E2%80%931340%2E)
7. Kristofer E. Bouchard and Michael S. Brainard. 2013. Neural Encoding and Integration of Learned Probabilistic Sequences in Avian Sensory-Motor Circuitry. The Journal of Neuroscience, 33(45):17710–17723. [find](https://scholar.google.com/scholar?q=Kristofer+E%2E+Bouchard+and+Michael+S%2E+Brainard%2E+2013%2E+Neural+Encoding+and+Integration+of+Learned+Probabilistic+Sequences+in+Avian+Sensory%2DMotor+Circuitry%2E+The+Journal+of+Neuroscience%2C+33%2845%29%3A17710%E2%80%931772)
8. Judit Gervain, Francesco Macagno, Silvia Cogoi, Marcela Peña, and Jacques Mehler. 2008. The neonate brain detects speech structure. Proceedings of the National Academy of Sciences of the United States of America, 105(37):14222–14227. [find](https://scholar.google.com/scholar?q=Judit+Gervain%2C+Francesco+Macagno%2C+Silvia+Cogoi%2C+Marcela+Pe%C3%B1a%2C+and+Jacques+Mehler%2E+2008%2E+The+neonate+brain+detects+speech+structure%2E+Proceedings+of+the+National+Academy+of+Sciences+of+the+United+States)
9. Neil Burgess and Graham J. Hitch. 1999. Memory for serial order: A network model of the phonological loop and its timing. Psychological Review, 106(3):551–581. [find](https://scholar.google.com/scholar?q=Neil+Burgess+and+Graham+J%2E+Hitch%2E+1999%2E+Memory+for+serial+order%3A+A+network+model+of+the+phonological+loop+and+its+timing%2E+Psychological+Review%2C+106%283%29%3A551%E2%80%93581%2E)
10. Laura Gwilliams, Jean-Remi King, Alec Marantz, and David Poeppel. 2022. Neural dynamics of phoneme sequences reveal position-invariant code for content and order. Nature Communications, 13(1):6606. [find](https://scholar.google.com/scholar?q=Laura+Gwilliams%2C+Jean%2DRemi+King%2C+Alec+Marantz%2C+and+David+Poeppel%2E+2022%2E+Neural+dynamics+of+phoneme+sequences+reveal+position%2Dinvariant+code+for+content+and+order%2E+Nature+Communications%2C+13%281%29%3A6606%2E)
11. Kyle E. Chambers, Kristine H. Onishi, and Cynthia Fisher. 2003. Infants learn phonotactic regularities from brief auditory experience. Cognition, 87(2):B69–B77. [find](https://scholar.google.com/scholar?q=Kyle+E%2E+Chambers%2C+Kristine+H%2E+Onishi%2C+and+Cynthia+Fisher%2E+2003%2E+Infants+learn+phonotactic+regularities+from+brief+auditory+experience%2E+Cognition%2C+87%282%29%3AB69%E2%80%93B77%2E)
12. Ira J. Hirsh. 1959. Auditory Perception of Temporal Order. The Journal of the Acoustical Society of America, 31(6):759–767. [find](https://scholar.google.com/scholar?q=Ira+J%2E+Hirsh%2E+1959%2E+Auditory+Perception+of+Temporal+Order%2E+The+Journal+of+the+Acoustical+Society+of+America%2C+31%286%29%3A759%E2%80%93767%2E)
13. Alexander M. Chan, Andrew R. Dykstra, Vinay Jayaram, Matthew K. Leonard, Katherine E. Travis, Brian Gygi, Janet M. Baker, Emad Eskandar, Leigh R. Hochberg, Eric Halgren, and Sydney S. Cash. 2014. Speech-Specific Tuning of Neurons in Human Superior Temporal Gyrus. Cerebral Cortex, 24(10):2679– 2693. [find](https://scholar.google.com/scholar?q=Alexander+M%2E+Chan%2C+Andrew+R%2E+Dykstra%2C+Vinay+Jayaram%2C+Matthew+K%2E+Leonard%2C+Katherine+E%2E+Travis%2C+Brian+Gygi%2C+Janet+M%2E+Baker%2C+Emad+Eskandar%2C+Leigh+R%2E+Hochberg%2C+Eric+Halgren%2C+and+Sydney+S%2E+Cash%2E+2014%2E+Spee)
14. Edward F. Chang, Jochem W. Rieger, Keith Johnson, Mitchel S. Berger, Nicholas M. Barbaro, and Robert T. Knight. 2010. Categorical speech representation in human superior temporal gyrus. Nature Neuroscience, 13(11):1428–1432. [find](https://scholar.google.com/scholar?q=Edward+F%2E+Chang%2C+Jochem+W%2E+Rieger%2C+Keith+Johnson%2C+Mitchel+S%2E+Berger%2C+Nicholas+M%2E+Barbaro%2C+and+Robert+T%2E+Knight%2E+2010%2E+Categorical+speech+representation+in+human+superior+temporal+gyrus%2E+Nature+Neurosc)
15. Marie Cheour, Rita Ceponiene, Anne Lehtokoski, Aavo Luuk, Jüri Allik, Kimmo Alho, and Risto Näätänen. 1998. Development of language-specific phoneme representations in the infant brain. Nature Neuroscience, 1(5):351–353. [find](https://scholar.google.com/scholar?q=Marie+Cheour%2C+Rita+Ceponiene%2C+Anne+Lehtokoski%2C+Aavo+Luuk%2C+J%C3%BCri+Allik%2C+Kimmo+Alho%2C+and+Risto+N%C3%A4%C3%A4t%C3%A4nen%2E+1998%2E+Development+of+language%2Dspecific+phoneme+representations+in+the+infant+brain%2E+Nature+Neurosc)
16. Giovanni M. Di Liberto, Adam Attaheri, Giorgia Can-tisani, Richard B. Reilly, Áine Ní Choisdealbha, Sinead Rocha, Perrine Brusini, and Usha Goswami. 2023. Emergence of the cortical encoding of phonetic features in the first year of life. Nature Communications, 14(1):7789. [find](https://scholar.google.com/scholar?q=Giovanni+M%2E+Di+Liberto%2C+Adam+Attaheri%2C+Giorgia+Can%2Dtisani%2C+Richard+B%2E+Reilly%2C+%C3%81ine+N%C3%AD+Choisdealbha%2C+Sinead+Rocha%2C+Perrine+Brusini%2C+and+Usha+Goswami%2E+2023%2E+Emergence+of+the+cortical+encoding+of+phoneti)
17. Jeff Hwang, Moto Hira, Caroline Chen, Xiaohui Zhang, Zhaoheng Ni, Guangzhi Sun, Pingchuan Ma, Ruizhe Huang, Vineel Pratap, Yuekai Zhang, Anurag Kumar, Chin-Yun Yu, Chuang Zhu, Chunxi Liu, Jacob Kahn, Mirco Ravanelli, Peng Sun, Shinji Watanabe, Yangyang Shi, and 5 others. 2023. TorchAudio 2.1: Advanc… — [arXiv:2310.17864](https://arxiv.org/abs/2310.17864) [find](https://scholar.google.com/scholar?q=Jeff+Hwang%2C+Moto+Hira%2C+Caroline+Chen%2C+Xiaohui+Zhang%2C+Zhaoheng+Ni%2C+Guangzhi+Sun%2C+Pingchuan+Ma%2C+Ruizhe+Huang%2C+Vineel+Pratap%2C+Yuekai+Zhang%2C+Anurag+Kumar%2C+Chin%2DYun+Yu%2C+Chuang+Zhu%2C+Chunxi+Liu%2C+Jacob+Kahn%2C+)
18. Menoua Keshishian, Serdar Akkol, Jose Herrero, Stephan Bickel, Ashesh D. Mehta, and Nima Mesgarani. 2023. Joint, distributed and hierarchically organized encoding of linguistic features in the human auditory cortex. Nature Human Behaviour, 7(5):740– 753. [find](https://scholar.google.com/scholar?q=Menoua+Keshishian%2C+Serdar+Akkol%2C+Jose+Herrero%2C+Stephan+Bickel%2C+Ashesh+D%2E+Mehta%2C+and+Nima+Mesgarani%2E+2023%2E+Joint%2C+distributed+and+hierarchically+organized+encoding+of+linguistic+features+in+the+human+a)
19. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. Version Number: 9. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2014%2E+Adam%3A+A+Method+for+Stochastic+Optimization%2E+Version+Number%3A+9%2E)
20. Patricia K. Kuhl, Erica Stevens, Akiko Hayashi, Toshisada Deguchi, Shigeru Kiritani, and Paul Iverson. 2006. Infants show a facilitation effect for native language phonetic perception between 6 and 12 months. Developmental Science, 9(2). [find](https://scholar.google.com/scholar?q=Patricia+K%2E+Kuhl%2C+Erica+Stevens%2C+Akiko+Hayashi%2C+Toshisada+Deguchi%2C+Shigeru+Kiritani%2C+and+Paul+Iverson%2E+2006%2E+Infants+show+a+facilitation+effect+for+native+language+phonetic+perception+between+6+and+12)
21. Ansgar D. Endress and Jacques Mehler. 2010. Perceptual constraints in phonotactic learning. Journal of Experimental Psychology: Human Perception and Performance, 36(1):235–250. [find](https://scholar.google.com/scholar?q=Ansgar+D%2E+Endress+and+Jacques+Mehler%2E+2010%2E+Perceptual+constraints+in+phonotactic+learning%2E+Journal+of+Experimental+Psychology%3A+Human+Perception+and+Performance%2C+36%281%29%3A235%E2%80%93250%2E)
22. Yair Lakretz, Ori Ossmy, Naama Friedmann, Roy Mukamel, and Itzhak Fried. 2021. Single-cell activity in human STG during perception of phonemes is organized according to manner of articulation. NeuroImage, 226:117499. [find](https://scholar.google.com/scholar?q=Yair+Lakretz%2C+Ori+Ossmy%2C+Naama+Friedmann%2C+Roy+Mukamel%2C+and+Itzhak+Fried%2E+2021%2E+Single%2Dcell+activity+in+human+STG+during+perception+of+phonemes+is+organized+according+to+manner+of+articulation%2E+NeuroIm)
23. Ana Fló. 2021. Evidence of ordinal position encoding of sequences extracted from continuous speech. Cognition, 213:104646. [find](https://scholar.google.com/scholar?q=Ana+Fl%C3%B3%2E+2021%2E+Evidence+of+ordinal+position+encoding+of+sequences+extracted+from+continuous+speech%2E+Cognition%2C+213%3A104646%2E)
24. Matthew K. Leonard, Kristofer E. Bouchard, Claire Tang, and Edward F. Chang. 2015. Dynamic Encoding of Speech Sequence Probability in Human Temporal Cortex. The Journal of Neuroscience, 35(18):7203–7214. [find](https://scholar.google.com/scholar?q=Matthew+K%2E+Leonard%2C+Kristofer+E%2E+Bouchard%2C+Claire+Tang%2C+and+Edward+F%2E+Chang%2E+2015%2E+Dynamic+Encoding+of+Speech+Sequence+Probability+in+Human+Temporal+Cortex%2E+The+Journal+of+Neuroscience%2C+35%2818%29%3A7203%E2%80%9372)
25. Matthew K. Leonard, Laura Gwilliams, Kristin K. Sellers, Jason E. Chung, Duo Xu, Gavin Mischler, Nima Mesgarani, Marleen Welkenhuysen, Barundeb Dutta, and Edward F. Chang. 2024. Large-scale single-neuron speech sound encoding across the depth of human cortex. Nature, 626(7999):593–602. [find](https://scholar.google.com/scholar?q=Matthew+K%2E+Leonard%2C+Laura+Gwilliams%2C+Kristin+K%2E+Sellers%2C+Jason+E%2E+Chung%2C+Duo+Xu%2C+Gavin+Mischler%2C+Nima+Mesgarani%2C+Marleen+Welkenhuysen%2C+Barundeb+Dutta%2C+and+Edward+F%2E+Chang%2E+2024%2E+Large%2Dscale+single%2Dneu)
26. David J. Lewkowicz. 2013. Development of ordinal sequence perception in infancy. Developmental Science, 16(3):352–364. [find](https://scholar.google.com/scholar?q=David+J%2E+Lewkowicz%2E+2013%2E+Development+of+ordinal+sequence+perception+in+infancy%2E+Developmental+Science%2C+16%283%29%3A352%E2%80%93364%2E)
27. Loren Lugosch, Mirco Ravanelli, Patrick Ignoto, Vikrant Singh Tomar, and Yoshua Bengio. 2019. Speech Model Pre-training for End-to-End Spoken Language Understanding. [find](https://scholar.google.com/scholar?q=Loren+Lugosch%2C+Mirco+Ravanelli%2C+Patrick+Ignoto%2C+Vikrant+Singh+Tomar%2C+and+Yoshua+Bengio%2E+2019%2E+Speech+Model+Pre%2Dtraining+for+End%2Dto%2DEnd+Spoken+Language+Understanding%2E)
28. Michael McAuliffe, Michaela Socolof, Sarah Mihuc, Michael Wagner, and Morgan Sonderegger. 2017. [find](https://scholar.google.com/scholar?q=Michael+McAuliffe%2C+Michaela+Socolof%2C+Sarah+Mihuc%2C+Michael+Wagner%2C+and+Morgan+Sonderegger%2E+2017%2E)
29. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi. In Proc. Interspeech 2017, pages 498–502. [find](https://scholar.google.com/scholar?q=Montreal+Forced+Aligner%3A+Trainable+Text%2DSpeech+Alignment+Using+Kaldi%2E+In+Proc%2E+Interspeech+2017%2C+pages+498%E2%80%93502%2E)
30. James L. McClelland. 2009. The Place of Modeling in Cognitive Science. Topics in Cognitive Science, 1(1):11–38. [find](https://scholar.google.com/scholar?q=James+L%2E+McClelland%2E+2009%2E+The+Place+of+Modeling+in+Cognitive+Science%2E+Topics+in+Cognitive+Science%2C+1%281%29%3A11%E2%80%9338%2E)
31. Nima Mesgarani, Connie Cheung, Keith Johnson, and Edward F. Chang. 2014. Phonetic Feature Encoding in Human Superior Temporal Gyrus. Science, 343(6174):1006–1010. [find](https://scholar.google.com/scholar?q=Nima+Mesgarani%2C+Connie+Cheung%2C+Keith+Johnson%2C+and+Edward+F%2E+Chang%2E+2014%2E+Phonetic+Feature+Encoding+in+Human+Superior+Temporal+Gyrus%2E+Science%2C+343%286174%29%3A1006%E2%80%931010%2E)
32. Nima Mesgarani, Stephen V. David, Jonathan B. Fritz, and Shihab A. Shamma. 2008. Phoneme representation and classification in primary auditory cortex. The Journal of the Acoustical Society of America, 123(2):899–909. [find](https://scholar.google.com/scholar?q=Nima+Mesgarani%2C+Stephen+V%2E+David%2C+Jonathan+B%2E+Fritz%2C+and+Shihab+A%2E+Shamma%2E+2008%2E+Phoneme+representation+and+classification+in+primary+auditory+cortex%2E+The+Journal+of+the+Acoustical+Society+of+America%2C)
33. Juliette Millet and Ewan Dunbar. 2020. The Perceptimatic English Benchmark for Speech Perception Models. arXiv preprint. [find](https://scholar.google.com/scholar?q=Juliette+Millet+and+Ewan+Dunbar%2E+2020%2E+The+Perceptimatic+English+Benchmark+for+Speech+Perception+Models%2E+arXiv+preprint%2E)
34. Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé, Morgane Rivière, Evgeny Kharitonov, Alexei Baevski, Ewan Dunbar, and Emmanuel Dupoux. 2020. [find](https://scholar.google.com/scholar?q=Tu+Anh+Nguyen%2C+Maureen+de+Seyssel%2C+Patricia+Roz%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+Evgeny+Kharitonov%2C+Alexei+Baevski%2C+Ewan+Dunbar%2C+and+Emmanuel+Dupoux%2E+2020%2E)
35. The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling. arXiv preprint. [find](https://scholar.google.com/scholar?q=The+Zero+Resource+Speech+Benchmark+2021%3A+Metrics+and+baselines+for+unsupervised+spoken+language+modeling%2E+arXiv+preprint%2E)
36. Yoshihisa Ninokura, Hajime Mushiake, and Jun Tanji. 2003. Representation of the Temporal Order of Visual Objects in the Primate Lateral Prefrontal Cortex. Journal of Neurophysiology, 89(5):2868–2873. [find](https://scholar.google.com/scholar?q=Yoshihisa+Ninokura%2C+Hajime+Mushiake%2C+and+Jun+Tanji%2E+2003%2E+Representation+of+the+Temporal+Order+of+Visual+Objects+in+the+Primate+Lateral+Prefrontal+Cortex%2E+Journal+of+Neurophysiology%2C+89%285%29%3A2868%E2%80%932873%2E)
37. Yoshihisa Ninokura, Hajime Mushiake, and Jun Tanji. 2004. Integration of Temporal Order and Object Information in the Monkey Lateral Prefrontal Cortex. Journal of Neurophysiology, 91(1):555–560. [find](https://scholar.google.com/scholar?q=Yoshihisa+Ninokura%2C+Hajime+Mushiake%2C+and+Jun+Tanji%2E+2004%2E+Integration+of+Temporal+Order+and+Object+Information+in+the+Monkey+Lateral+Prefrontal+Cortex%2E+Journal+of+Neurophysiology%2C+91%281%29%3A555%E2%80%93560%2E)
38. Tanya Orlov, Volodya Yakovlev, Shaul Hochstein, and Ehud Zohary. 2000. Macaque monkeys categorize images by their ordinal number. Nature, 404(6773):77–80. [find](https://scholar.google.com/scholar?q=Tanya+Orlov%2C+Volodya+Yakovlev%2C+Shaul+Hochstein%2C+and+Ehud+Zohary%2E+2000%2E+Macaque+monkeys+categorize+images+by+their+ordinal+number%2E+Nature%2C+404%286773%29%3A77%E2%80%9380%2E)
39. Tobias Overath, Rhodri Cusack, Sukhbinder Kumar, Katharina Von Kriegstein, Jason D Warren, Manon Grube, Robert P Carlyon, and Timothy D Griffiths. 2007. An Information Theoretic Characterisation of Auditory Encoding. PLoS Biology, 5(11):e288. [find](https://scholar.google.com/scholar?q=Tobias+Overath%2C+Rhodri+Cusack%2C+Sukhbinder+Kumar%2C+Katharina+Von+Kriegstein%2C+Jason+D+Warren%2C+Manon+Grube%2C+Robert+P+Carlyon%2C+and+Timothy+D+Griffiths%2E+2007%2E+An+Information+Theoretic+Characterisation+of+Au)
40. Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. 2015. Librispeech: An ASR corpus based on public domain audio books. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5206–5210, South Brisbane, Queensland, Australia. IEEE. [find](https://scholar.google.com/scholar?q=Vassil+Panayotov%2C+Guoguo+Chen%2C+Daniel+Povey%2C+and+Sanjeev+Khudanpur%2E+2015%2E+Librispeech%3A+An+ASR+corpus+based+on+public+domain+audio+books%2E+In+2015+IEEE+International+Conference+on+Acoustics%2C+Speech+and+)
41. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, and 2 others. 2019.… [find](https://scholar.google.com/scholar?q=Adam+Paszke%2C+Sam+Gross%2C+Francisco+Massa%2C+Adam+Lerer%2C+James+Bradbury%2C+Gregory+Chanan%2C+Trevor+Killeen%2C+Zeming+Lin%2C+Natalia+Gimelshein%2C+Luca+Antiga%2C+Alban+Desmaison%2C+Andreas+K%C3%B6pf%2C+Edward+Yang%2C+Zach+DeVit) [our card](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/)
42. Maritza Rivera-Gaxiola, Juan Silva-Pereyra, and Patricia K. Kuhl. 2005. Brain potentials to native and non-native speech contrasts in 7- and 11-month-old American infants. Developmental Science, 8(2):162– 172. [find](https://scholar.google.com/scholar?q=Maritza+Rivera%2DGaxiola%2C+Juan+Silva%2DPereyra%2C+and+Patricia+K%2E+Kuhl%2E+2005%2E+Brain+potentials+to+native+and+non%2Dnative+speech+contrasts+in+7%2D+and+11%2Dmonth%2Dold+American+infants%2E+Developmental+Science%2C+8%282%29%3A)
43. Jenny R. Saffran, Richard N. Aslin, and Elissa L. Newport. 1996. Statistical Learning by 8-Month-Old Infants. Science, 274(5294):1926–1928. [find](https://scholar.google.com/scholar?q=Jenny+R%2E+Saffran%2C+Richard+N%2E+Aslin%2C+and+Elissa+L%2E+Newport%2E+1996%2E+Statistical+Learning+by+8%2DMonth%2DOld+Infants%2E+Science%2C+274%285294%29%3A1926%E2%80%931928%2E)
44. Jenny R. Saffran and Natasha Z. Kirkham. 2018. Infant Statistical Learning. Annual Review of Psychology, 69(1):181–203. [find](https://scholar.google.com/scholar?q=Jenny+R%2E+Saffran+and+Natasha+Z%2E+Kirkham%2E+2018%2E+Infant+Statistical+Learning%2E+Annual+Review+of+Psychology%2C+69%281%29%3A181%E2%80%93203%2E)
45. Kapil Saini and Ajmer Singh. 2024. A content-based recommender system using stacked LSTM and an attention-based autoencoder. Measurement: Sensors, 31:100975. [find](https://scholar.google.com/scholar?q=Kapil+Saini+and+Ajmer+Singh%2E+2024%2E+A+content%2Dbased+recommender+system+using+stacked+LSTM+and+an+attention%2Dbased+autoencoder%2E+Measurement%3A+Sensors%2C+31%3A100975%2E)
46. Thomas Schatz, Francis Bach, and Emmanuel Dupoux. 2018. Evaluating automatic speech recognition systems as quantitative models of cross-lingual phonetic category perception. The Journal of the Acoustical Society of America, 143(5):EL372–EL378. [find](https://scholar.google.com/scholar?q=Thomas+Schatz%2C+Francis+Bach%2C+and+Emmanuel+Dupoux%2E+2018%2E+Evaluating+automatic+speech+recognition+systems+as+quantitative+models+of+cross%2Dlingual+phonetic+category+perception%2E+The+Journal+of+the+Acousti)
47. Thomas Schatz, Vijayaditya Peddinti, Francis Bach, Aren Jansen, Hynek Hermansky, and Emmanuel Dupoux. 2013. Evaluating speech features with the Minimal-Pair ABX task: Analysis of the classical MFC/PLP pipeline. In Proceedings of INTER-SPEECH 2013, pages 1–5, Lyon, France. [find](https://scholar.google.com/scholar?q=Thomas+Schatz%2C+Vijayaditya+Peddinti%2C+Francis+Bach%2C+Aren+Jansen%2C+Hynek+Hermansky%2C+and+Emmanuel+Dupoux%2E+2013%2E+Evaluating+speech+features+with+the+Minimal%2DPair+ABX+task%3A+Analysis+of+the+classical+MFC%2FPLP)
48. Jan W. H. Schnupp, Thomas M. Hall, Rory F. Koke-laar, and Bashir Ahmed. 2006. Plasticity of Temporal Pattern Codes for Vocalization Stimuli in Primary Auditory Cortex. The Journal of Neuroscience, 26(18):4785–4795. [find](https://scholar.google.com/scholar?q=Jan+W%2E+H%2E+Schnupp%2C+Thomas+M%2E+Hall%2C+Rory+F%2E+Koke%2Dlaar%2C+and+Bashir+Ahmed%2E+2006%2E+Plasticity+of+Temporal+Pattern+Codes+for+Vocalization+Stimuli+in+Primary+Auditory+Cortex%2E+The+Journal+of+Neuroscience%2C+26%28)
49. Anna Shestakova, Elvira Brattico, Alexei Soloviev, Vasily Klucharev, and Minna Huotilainen. 2004. Orderly cortical representation of vowel categories presented by multiple exemplars. Brain Research. Cognitive Brain Research, 21(3):342–350. [find](https://scholar.google.com/scholar?q=Anna+Shestakova%2C+Elvira+Brattico%2C+Alexei+Soloviev%2C+Vasily+Klucharev%2C+and+Minna+Huotilainen%2E+2004%2E+Orderly+cortical+representation+of+vowel+categories+presented+by+multiple+exemplars%2E+Brain+Research%2E+C)
50. Benjamin Skerritt-Davis and Mounya Elhilali. 2018. Detecting change in stochastic sound sequences. PLOS Computational Biology, 14(5):e1006162. [find](https://scholar.google.com/scholar?q=Benjamin+Skerritt%2DDavis+and+Mounya+Elhilali%2E+2018%2E+Detecting+change+in+stochastic+sound+sequences%2E+PLOS+Computational+Biology%2C+14%285%29%3Ae1006162%2E)
51. M. Steinschneider. 2005. Intracortical Responses in Human and Monkey Primary Auditory Cortex Support a Temporal Processing Mechanism for Encoding of the Voice Onset Time Phonetic Parameter. Cerebral Cortex, 15(2):170–186. [find](https://scholar.google.com/scholar?q=M%2E+Steinschneider%2E+2005%2E+Intracortical+Responses+in+Human+and+Monkey+Primary+Auditory+Cortex+Support+a+Temporal+Processing+Mechanism+for+Encoding+of+the+Voice+Onset+Time+Phonetic+Parameter%2E+Cerebral+C)
52. Megha Sundara, Linda Polka, and Fred Genesee. 2006. Language-experience facilitates discrimination of /d-/ in monolingual and bilingual acquisition of English. Cognition, 100(2):369–388. [find](https://scholar.google.com/scholar?q=Megha+Sundara%2C+Linda+Polka%2C+and+Fred+Genesee%2E+2006%2E+Language%2Dexperience+facilitates+discrimination+of+%2Fd%2D%2F+in+monolingual+and+bilingual+acquisition+of+English%2E+Cognition%2C+100%282%29%3A369%E2%80%93388%2E)
53. Frank Lihui Tan and Youngah Do. 2025. Attention-LSTM autoencoder simulation for phonotactic learning from raw audio input. Linguistics Vanguard. [find](https://scholar.google.com/scholar?q=Frank+Lihui+Tan+and+Youngah+Do%2E+2025%2E+Attention%2DLSTM+autoencoder+simulation+for+phonotactic+learning+from+raw+audio+input%2E+Linguistics+Vanguard%2E)
54. Erik D. Thiessen and Jenny R. Saffran. 2003. When cues collide: Use of stress and statistical cues to word boundaries by 7- to 9-month-old infants. Developmental Psychology, 39(4):706–716. [find](https://scholar.google.com/scholar?q=Erik+D%2E+Thiessen+and+Jenny+R%2E+Saffran%2E+2003%2E+When+cues+collide%3A+Use+of+stress+and+statistical+cues+to+word+boundaries+by+7%2D+to+9%2Dmonth%2Dold+infants%2E+Developmental+Psychology%2C+39%284%29%3A706%E2%80%93716%2E)
55. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N%2E+Gomez%2C+Lukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+Is+All+You+Need%2E)
56. Gail Weiss, Yoav Goldberg, and Eran Yahav. 2018. On the Practical Computational Power of Finite Precision RNNs for Language Recognition. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 740–745, Melbourne, Australia. Associati… [find](https://scholar.google.com/scholar?q=Gail+Weiss%2C+Yoav+Goldberg%2C+and+Eran+Yahav%2E+2018%2E+On+the+Practical+Computational+Power+of+Finite+Precision+RNNs+for+Language+Recognition%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+fo) [our card](https://md.research.elamur.ai/free/en/papers/weiss-2018-practical-computational-power-finite-precision/)
57. Da Ren Zhang, Zhi Hao Li, Xiang Chuan Chen, Zhao Xin Wang, Xiao Chu Zhang, Xiao Mei Meng, Sheng He, and Xiao Ping Hu. 2003. Functional comparison of primacy, middle and recency retrieval in human auditory short-term memory: an event-related fMRI study. Cognitive Brain Research, 16(1):91–98. [find](https://scholar.google.com/scholar?q=Da+Ren+Zhang%2C+Zhi+Hao+Li%2C+Xiang+Chuan+Chen%2C+Zhao+Xin+Wang%2C+Xiao+Chu+Zhang%2C+Xiao+Mei+Meng%2C+Sheng+He%2C+and+Xiao+Ping+Hu%2E+2003%2E+Functional+comparison+of+primacy%2C+middle+and+recency+retrieval+in+human+audi)