Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Towards Zero-Shot Learning for Automatic Phonemic Transcription
Xinjian Li, Siddharth Dalmia, David Mortensen, Juncheng Li, Alan Black, Florian Metze
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use articulatory-attribute prediction and a language-specific phoneme signature matrix instead of a shared phoneme output inventory | Multilingual acoustic model · 7-language average | PER (%): 66.9 -> 59.2 | Improved |
| Use articulatory-attribute prediction and a language-specific phoneme signature matrix | Multilingual acoustic model · 7-language average | Substitution error (%): 40.2 -> 31.9 | Improved |
| Use articulatory-attribute prediction to infer unseen phonemes | Multilingual acoustic model · 7-language average, unseen phonemes | PER (%): 100.0 -> 89.8 | Improved |
| Use articulatory-attribute prediction | Multilingual acoustic model · 7-language average, seen phonemes | PER (%): 64.2 -> 57.0 | Improved |
| Increase the number of training languages (ablation) | UPM and multilingual baseline · 7-language average | PER (%) | Improved |
| Use more training languages with UPM rather than the multilingual baseline (ablation) | UPM versus multilingual baseline · 7-language average | PER gap: 5.0 to 9.3 | Improved |
Closest papers by meaning
- LAMA-UT: Language Agnostic Multilingual ASR Through Orthography Unification and Language-Specific Transliteration (AAAI 2025 · similarity 0.86)
- CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech (ICLR 2024 · similarity 0.86)
- Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis (ICLR 2024 · similarity 0.85)
- SyllableLM: Learning Coarse Semantic Units for Speech Language Models (ICLR 2025 · similarity 0.85)
- Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement (ICLR 2025 · similarity 0.85)
- Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-Speech (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
