No article text was recorded for this version.
cross-lingual generalization gap (monolingual training bias)
Version 1 of 124 papers26 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks
- Blog: Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS
- Blog: SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion
- Blog: mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition
- Blog: Zero-Shot Cross-Lingual Phonetic Recognition with External Language Embedding
- Blog: HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling
- Blog: Zero-shot cross-lingual identification of direct speech using distant supervision
- Blog: Towards a Common Speech Analysis Engine
- Blog: SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models
- Blog: Coding Speech Through Vocal Tract Kinematics
- Blog: Rate-Aware Learned Speech Compression
- Blog: Learning Neural Network Representations Using Cross-Lingual Bottleneck Features with Word-Pair Information
- Blog: MDAR: A Multi-scene Dynamic Audio Reasoning Benchmark
- Blog: Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
- Blog: Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
- Blog: CTC-Assisted LLM-Based Contextual ASR
- Blog: WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- Blog: Musical Word Embedding for Music Tagging and Retrieval
- Blog: Disentangled Latent Speech Representation for Automatic Pathological Intelligibility Assessment
- Blog: Exploring the Limits of Conformer CTC-Encoder for Speech Emotion Recognition using Large Language Models
- Blog: SpeechOp: Inference-Time Task Composition for Generative Speech Processing
- Blog: Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
- Blog: SELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios
- Blog: Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition
History & citation
Current · Permanent link
- This direction split from Multilingual Generalization for Speech Foundation Models (75% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_lingual_generalization_gap_monolin_c91671b9,
title = {cross-lingual generalization gap (monolingual training bias)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-lingual-generalization-gap-monolingual-training-bias/rdr_c91671b997204f60828926e2585057e0},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_lingual_generalization_gap_monolin_c91671b9_v1,
title = {cross-lingual generalization gap (monolingual training bias)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-lingual-generalization-gap-monolingual-training-bias/rdr_c91671b997204f60828926e2585057e0/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}