Hugging Face Trending Papers

Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning

Read the original on Hugging Face Trending Papers →

Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalistic recordings remain challenging due to limited labeled data, low signal-to-noise ratio, and cross-family domain shifts. We present a family-conditioned, multi-tier audio tagger that combines a LoRA-finetuned Whisper encoder with a lightweight, target-speaker-aware Transformer for long-context inference and framewise prediction across tiers.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
6d ago

Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning

arXiv:2608. 11587v1 Announce Type: cross Abstract: Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalistic recordings remain challenging due to limited labeled data, low signal-to-noise ratio, and cross-family domain shifts.

By Xulin Fan, Jialu Li, Mohammad Nur Hossain Khan, Kexin Hu, Bashima Islam, Mark Hasegawa-Johnson, Nancy L. McElwain
arXiv Machine Learning
Jul 24

Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization

arXiv:2602. 10230v2 Announce Type: replace Abstract: Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding.

By Joseph An, Phillip Keung, Jiaqi Wang, Orevaoghene Ahia, Noah A. Smith
Hugging Face Trending Papers
Jun 3

CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding

Neural audio codecs are a key component of speech processing pipelines, compressing audio into discrete tokens for downstream modeling. However, existing codecs struggle to balance reconstruction quality with token efficiency, often encoding perceptually irrelevant information such as background noise and recording artifacts at the expense of linguistically and acoustically meaningful content.