← Back to all news
arXiv Computation and Language By Minnie Kabra, Benjamin Lecouteux, Maximin Coavoux

When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech Parsing

Read the original on arXiv Computation and Language →

The paper investigates the role of intermediate neural networks in end‑to‑end speech parsing, a task that jointly predicts transcription and syntactic structure. By removing these intermediate units, the authors reduce model parameters by 12% while matching or surpassing prior performance on ASR and parsing across French, Slovenian, and Naija. They find that intermediate layers mainly help close the representational gap when the pretrained encoder is frozen and analyze how training data size and encoder depth affect parsing performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Oct 8

Phoneme-Guided Initialization for LLM-based Speech Recognition

The paper introduces phoneme‑guided initialization for large language model‑based speech recognition. By pre‑training an audio encoder on speech‑to‑phoneme conversion and an LLM on phoneme‑to‑grapheme conversion, then fine‑tuning jointly on ASR, the method leverages phoneme‑mediated processing within an end‑to‑end framework. Experiments on Japanese, Chinese, Tatar, and Urdu demonstrate that this approach matches or surpasses both cascaded S2P‑P2G baselines and end‑to‑end models without phoneme initialization.

By Ryo Magoshi, Shinsuke Sakai, Tatsuya Kawahara
llmsfine-tuningmultimodal
More like this →
arXiv Computation and Language
Sep 28

Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring

The paper introduces a training‑free speech‑and‑text‑to‑pronunciation (ST2P) pipeline that combines lexical candidates from G2P tools with acoustic rescoring using frozen pretrained S2P models. By performing a left‑to‑right greedy search over whole‑sequence negative log‑likelihoods, the method achieves a dramatic reduction in character error rate on Japanese corpora, outperforming both baseline G2P/S2P approaches and commercial multimodal LLMs. The approach is also significantly faster—3–3.5× faster than beam search and twice as fast as direct decoding—while maintaining high accuracy across multiple languages.

By Hikaru Asano, Yotaro Kubo, So Kuroki
llmsmultimodal
More like this →
arXiv Computation and Language
Oct 15

Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy

arXiv:2610.19492v1 Announce Type: new Abstract: Streaming Inverse Text Normalization (ITN) is vital for converting spoken-form outputs from streaming Automatic Speech Recognition into formatted writt...

By Kiet Anh Hoang, Khanh Le, Bao Nguyen, Linh Pham, Dung Vo, Thai Tran, Mai Nguyen, Tri Nguyen, Vu Le
llmsmultimodal
More like this →