No article text was recorded for this version.
architectural depth constraints (shallow architecture constraints)
Version 2 of 232 papers32 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Steerable Playlist Generation by Learning Song Similarity from Radio Station Playlists
- Blog: Hierarchical Mixtures of Experts Methodology Applied to Continuous Speech Recognition
- Blog: Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation
- Blog: Combating reverberation in large vocabulary continuous speech recognition
- Blog: Improved MLP structures for data-driven feature extraction for ASR
- Blog: Deep CNNs Along the Time Axis With Intermap Pooling for Robustness to Spectral Variations
- Blog: Very Deep Convolutional Networks for End-to-End Speech Recognition
- Blog: Conversational Speech Transcription Using Context-Dependent Deep Neural Networks
- Blog: Exploiting Depth and Highway Connections in Convolutional Recurrent Deep Neural Networks for Speech Recognition
- Blog: Adversarial Training for Multi-domain Speaker Recognition
- Blog: TDTO language modeling with feedforward neural networks
- Blog: Speech bandwidth expansion based on deep neural networks
- Blog: Tandem representations of spectral envelope and modulation frequency features for ASR
- Blog: Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
- Blog: A robust frontend for VAD: exploiting contextual, discriminative and spectral cues of human voice
- Blog: Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
- Blog: Slow-Fast Auditory Streams For Audio Recognition
- Blog: NEC-TT Speaker Verification System for SRE'19 CTS Challenge
- Blog: Applications of Error Back-Propagation to Phonetic Classification
- Blog: Pooling Robust Shift-Invariant Sparse Representations of Acoustic Signals
- Blog: Articulatory movement prediction using deep bidirectional long short-term memory based recurrent neural networks and word/phone embeddings
- Blog: TRAP language identification system for RATS phase II evaluation
- Blog: Are Sparse Representations Rich Enough for Acoustic Modeling?
- Blog: Sequence error (SE) minimization training of neural network for voice conversion
- Blog: Very Deep Multilingual Convolutional Neural Networks for LVCSR
- Blog: Speech Recognition Experiments with Perceptrons
- Blog: A Spiking Neural Network Framework for Robust Sound Classification
- Blog: ARET: Aggregated Residual Extended Time-Delay Neural Networks for Speaker Verification
- Blog: Joint Online Spoken Language Understanding and Language Modeling With Recurrent Neural Networks
- Blog: Deep Architecture Enhancing Robustness to Noise, Adversarial Attacks, and Cross-Corpus Setting for Speech Emotion Recognition
- Blog: Very deep convolutional neural networks for LVCSR
- Blog: Voice conversion using generative trained deep neural networks with multiple frame spectral envelopes
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_depth_constraints_shallow__07d0cfbe,
title = {architectural depth constraints (shallow architecture constraints)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-depth-constraints-shallow-architecture-constraints/rdr_07d0cfbe5bec421a9844a8f8d4de9873},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_architectural_depth_constraints_shallow__07d0cfbe_v2,
title = {architectural depth constraints (shallow architecture constraints)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-depth-constraints-shallow-architecture-constraints/rdr_07d0cfbe5bec421a9844a8f8d4de9873/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}