← Back to all news
arXiv Computation and Language

CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition

The paper introduces CAFE, a method that confines Centered Kernel Alignment (CKA) feature distillation to language‑routed adapters in compact multilingual ASR models. By restricting the CKA gradient to adapters that English bypasses, CAFE mitigates the trade‑off where CKA improves non‑English WER at the cost of English performance. On the Open ASR Leaderboard, CAFE reduces average WER from 8.55% to 8.02% and outperforms an adapter‑only capacity control, achieving competitive results across 48 test sets in 24 languages with 254M parameters.

Related stories

arXiv Computation and Language
2d ago

WaxalNet: Benchmarking and Adapting Speech Recognition for Spontaneous Speech in 19 African Languages

The paper introduces WaxalNet, a benchmark and adaptation study for spontaneous speech recognition across 19 African languages using the WAXAL corpus. It evaluates zero‑shot and fine‑tuned performance of several multilingual foundation models (Whisper, MMS, Omnilingual ASR, SeamlessM4T‑v2), showing that fine‑tuning can substantially reduce word error rates and that LLM decoders generally outperform CTC decoders when the encoder is shared. The authors also demonstrate that a single multilingual model can serve all languages with only a modest WER penalty and provide a native‑speaker audit of failure modes.

By Victor Tolulope Olufemi, Oreoluwa Babatunde, Ramsey Njema, Bolarinwa Gbotemi, Wanchi Lucia Yen, John Uzodinma, Sunday Ajayi, Oluwademilade Williams, Kausar Moshood, Innocent Elendu Anyaele, Akebert Arefaine, Candace Hunzwi, Wongel Dawit Daniel, Emmilly Namuganga, Cleophas Kadima, Athanase Bahizire, Onitsiky Ranaivoson, Emmanuel Aaron, Nicholaus Ladislaus, Idris Muhammed, Jonathan Enoch Simenya, Martin Koome, Matewos Tegete Endaylalu, Peter Ifeoluwa Adeyemo, Hondi Prisca Birindwa, Ukachi Agnes Eze-Mbey, Yacoba Oduro-Yeboah, Pericles Adjovi, Mikel K. Ngueajio, Toluwani Aremu, Prasenjit Mitra
llmsfine-tuningmultimodalbenchmarks
More like this →
arXiv Machine Learning
Oct 8

Child ASR Adaptation with Adult Retention: An Empirical Study

The study investigates how to adapt automatic speech recognition (ASR) models to child speech while preserving adult performance, focusing on Arabic and English data. It compares full fine‑tuning, LoRA, and post‑hoc weight‑space merging across encoder–decoder, encoder–CTC, and AudioLLM‑based ASR systems, using child and adult benchmarks. Results indicate that child adaptation is essential, especially for non‑native speakers, but direct adaptation can degrade adult accuracy; bilingual adaptation and weight‑space merging techniques help balance the trade‑off, with encoder–decoder fine‑tuning still yielding the best raw WER for bilingual models.

By Houssam Eddine-Othman Lachemat, Shammur Absar Chowdhury
fine-tuningmultimodalbenchmarks
More like this →
arXiv Computation and Language
Sep 25

A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition

The paper introduces a token‑level extension of Omni‑Temporal Classification (OTC) for automatic speech recognition, allowing unsupported tokens to be bypassed while preserving supervision for the rest of the word. Across 19 languages and three corpora, this token‑level OTC consistently outperforms standard CTC, achieving the lowest mean word error rate on every dataset and a 9.45% average relative WER reduction. A predictive‑entropy‑indexed schedule replaces epoch‑based relaxation, reducing training‑length dependence while maintaining performance.

By Saurabh Kumar, Diptiman Mohanta, Prasanta Kumar Ghosh
multimodalsafety
More like this →
arXiv AI
Sep 12

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

X-AuT is a progressive framework for compressing the audio encoder of speech large language models. It selects layer combinations via short behavioral probes and restores performance through representation alignment, cross‑scale distillation, scheduled student‑policy supervision, and LoRA finetuning, while keeping the language‑model backbone frozen. On ten Chinese–English benchmarks, reducing Qwen3‑ASR‑0.6B’s encoder from 18 to 16 layers lowers macro‑average error from 5.61% to 5.27%, and a 14‑layer model achieves 5.75% error with 20.7% fewer parameters.

By Haojun Zhang, Yi Zou, Min Chen, Qize Yu, Lianrui Fan, Xini Ding, Hao Li, Shuchang Zhou, Xianming Liu, Shiyu Huang
llmsragfine-tuningefficiencymultimodalbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 25

BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization

BranchShine-CR is a 25‑million‑parameter model that transcribes multilingual speech into the International Phonetic Alphabet (IPA). It uses log‑mel features, a rotary‑position E‑Branchformer encoder, intermediate self‑conditioned CTC, and consistency regularization across augmented views. On 16,646 shared IPApack++ test utterances it achieves a 4.47 % IPA character error rate, a 22.3 % relative improvement over ZIPA‑CTC‑NS and outperforms a similarly sized NeMo Conformer baseline across all 41 language labels.

By Nikhil Navas, Sergio Chevtchenko, Talisson Damiao, Saeed Afshar
benchmarks
More like this →