No article text was recorded for this version.
synthetic-to-real domain gap (synthetic-to-natural speech gap)
Version 1 of 1174 papers206 conceptsfrozen 2026-10-04
Papers in this version
- Blog: EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models
- Blog: Leveraging Out-of-Task Data for End-to-End Automatic Speech Translation
- Blog: Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation
- Blog: EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models
- Blog: YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection
- Blog: Unlocking Foundation Models for Privacy-Enhancing Speech Understanding: An Early Study on Low Resource Speech Training Leveraging Label-guided Synthetic Speech Content
- Blog: Speech Aware Dialog System Technology Challenge (DSTC11)
- Blog: Speech-Based Visual Question Answering
- Blog: Unlocking Foundation Models for Privacy-Enhancing Speech Understanding: An Early Study on Low Resource Speech Training Leveraging Label-guided Synthetic Speech Content
- Blog: Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
- Blog: Semi-supervised learning of glottal pulse positions in a neural analysis-synthesis framework
- Blog: Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
- Blog: Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech
- Blog: Frame-Level Stutter Detection
- Blog: Knowledge Distillation for Improved Accuracy in Spoken Question Answering
- Blog: Fully Unsupervised Training of Few-shot Keyword Spotting
- Blog: ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion
- Blog: Using Speech Synthesis to Train End-To-End Spoken Language Understanding Models
- Blog: Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain Adaptation
- Blog: Speech Aware Dialog System Technology Challenge (DSTC11)
- Blog: Code-Switching Text Generation and Injection in Mandarin-English ASR
- Blog: Improving Low Resource Code-Switched ASR Using Augmented Code-Switched TTS
- Blog: Stutter-Solver: End-to-end Multi-lingual Dysfluency Detection
- Blog: Improving Speech-to-Speech Translation Through Unlabeled Text
- Blog: Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems
- Blog: Mitigating Noisy Inputs for Question Answering
- Blog: Disentangling Indirect Answers to Yes-No Questions in Real Conversations
- Blog: It's Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systems
- Blog: MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark
- Blog: MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark
- Blog: Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- Blog: ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark
- Blog: Articulatory phonological code for word classification
- Blog: GSQA: An End-to-End Model for Generative Spoken Question Answering
- Blog: Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages
- Blog: RNN Transducer Models For Spoken Language Understanding
- Blog: SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning
- Blog: FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model
- Blog: Improving Speech Recognition Using GAN-Based Speech Synthesis and Contrastive Unspoken Text Selection
- Blog: When Is TTS Augmentation Through a Pivot Language Useful?
- Blog: Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM
- Blog: Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension
- Blog: SQuAD-SRC: A Dataset for Multi-Accent Spoken Reading Comprehension
- Blog: Minimum Cut Model for Spoken Lecture Segmentation
- Blog: Enhancing Speech-to-Speech Translation with Multiple TTS Targets
- Blog: Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
- Blog: LLaSM: Large Language and Speech Model
- Blog: Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding
- Blog: DUB: Discrete Unit Back-translation for Speech Translation
- Blog: Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
- Blog: Adversarial Training for Low-Resource Disfluency Correction
- Blog: Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation
- Blog: Textless Speech-to-Speech Translation on Real Data
- Blog: Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
- Blog: An Investigation Into Explainable Audio Hate Speech Detection
- Blog: SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models
- Blog: YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection
- Blog: Developing a Flexible Spoken Dialog System Using Simulation
- Blog: MUTEX: Learning Unified Policies from Multimodal Task Specifications
- Blog: In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations
Showing 60 of 174 papers.
History & citation
Current · Permanent link
- Closing the Synthetic to Natural Speech Gap merged into this direction (61% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_synthetic_to_real_domain_gap_synthetic_t_db080c38,
title = {synthetic-to-real domain gap (synthetic-to-natural speech gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/synthetic-to-real-domain-gap-synthetic-to-natural-speech-gap/rdr_db080c3820384e5a839f76f1493c5b0d},
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_synthetic_to_real_domain_gap_synthetic_t_db080c38_v1,
title = {synthetic-to-real domain gap (synthetic-to-natural speech gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/synthetic-to-real-domain-gap-synthetic-to-natural-speech-gap/rdr_db080c3820384e5a839f76f1493c5b0d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}