No article text was recorded for this version.
data diversity for generalization
Version 1 of 161 papers72 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Learning Complex Spectral Mapping for Speech Enhancement with Improved Cross-Corpus Generalization
- Blog: DDS: A new device-degraded speech dataset for speech enhancement
- Blog: Svarah: Evaluating English ASR Systems on Indian Accents
- Blog: BalsuTalka.lv - Boosting the Common Voice Corpus for Low-Resource Languages
- Blog: Towards Achieving Robust Universal Neural Vocoding
- Blog: Employing self-supervised learning models for cross-linguistic child speech maturity classification
- Blog: Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler
- Blog: Towards objective and interpretable speech disorder assessment: a comparative analysis of CNN and transformer-based models
- Blog: Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings
- Blog: N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
- Blog: Automatic cognitive assessment: Combining sparse datasets with disparate cognitive scores
- Blog: Improving Automatic Recognition of Aphasic Speech with AphasiaBank
- Blog: ConferencingSpeech 2022 Challenge: Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge for Online Conferencing Applications
- Blog: EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
- Blog: Single-Channel Dereverberation Using Direct MMSE Optimization and Bidirectional LSTM Networks
- Blog: DNN No-Reference PSTN Speech Quality Prediction
- Blog: Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations
- Blog: Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam
- Blog: Pushing the Limits of End-to-End Diarization
- Blog: Loquacious Set: 25, 000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use
- Blog: On Multi-Domain Training and Adaptation of End-to-End RNN Acoustic Models for Distant Speech Recognition
- Blog: CN-Celeb: Multi-genre speaker recognition
- Blog: EMOCONV-DIFF: Diffusion-based Speech Emotion Conversion for Non-parallel and In-the-wild Data
- Blog: ZSDEVC: Zero-Shot Diffusion-based Emotional Voice Conversion with Disentangled Mechanism
- Blog: UNIQUE : Unsupervised Network for Integrated Speech Quality Evaluation
- Blog: VoxCeleb2: Deep Speaker Recognition
- Blog: Is your model big enough? Training and interpreting large-scale monolingual speech foundation models
- Blog: Audiocite.net : A Large Spoken Read Dataset in French
- Blog: LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
- Blog: I Can Hear You: Selective Robust Training for Deepfake Audio Detection
- Blog: Towards Building Text-to-Speech Systems for the Next Billion Users
- Blog: The University of Birmingham 2017 SLaTE CALL Shared Task Systems
- Blog: Improving Gender Identification in Movie Audio Using Cross-Domain Data
- Blog: GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement
- Blog: Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification
- Blog: An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
- Blog: Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement
- Blog: Online Speaker Adaptation for WaveNet-based Neural Vocoders
- Blog: Multi-Level Temporal-Channel Speaker Retrieval for Zero-Shot Voice Conversion
- Blog: The Airbus Air Traffic Control Speech Recognition 2018 Challenge: Towards ATC Automatic Transcription and Call Sign Detection
- Blog: Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
- Blog: YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus
- Blog: Disordered Speech Data Collection: Lessons Learned at 1 Million Utterances from Project Euphonia
- Blog: Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
- Blog: Towards Secure User Authentication for Headphones via In-Ear or In-Earcup Microphones
- Blog: NMF-based speech enhancement incorporating deep neural network
- Blog: Audiocite.net un grand corpus d'enregistrements vocaux de lecture en français
- Blog: AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
- Blog: FT-Boosted SV: Towards Noise Robust Speaker Verification for English Speaking Classroom Environments
- Blog: Global SNR Estimation of Speech Signals Using Entropy and Uncertainty Estimates from Dropout Networks
- Blog: Robust Laughter Segmentation with Automatic Diverse Data Synthesis
- Blog: Learning Robust and Multilingual Speech Representations
- Blog: KSC2: An Industrial-Scale Open-Source Kazakh Speech Corpus
- Blog: Multi-Corpus Acoustic-to-Articulatory Speech Inversion
- Blog: Finding the Human Voice in AI: Insights on the Perception of AI-Voice Clones from Naturalness and Similarity Ratings
- Blog: Data Selection for Within-Class Covariance Estimation
- Blog: Unsupervised Fine-Tuning Data Selection for ASR Using Self-Supervised Speech Models
- Blog: Exploring goodness of prosody by diverse matching templates
- Blog: Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR
- Blog: On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models
Showing 60 of 61 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_data_diversity_for_generalization_b7261977,
title = {data diversity for generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/data-diversity-for-generalization/rdr_b7261977e8ca4255b0eb20a8d7b7938d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_data_diversity_for_generalization_b7261977_v1,
title = {data diversity for generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/data-diversity-for-generalization/rdr_b7261977e8ca4255b0eb20a8d7b7938d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}