AI Paper Atlas

Research map / Video / Video segmentation and tracking

FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates

Jiaqi Li, Yao Qian, Yuxuan Hu, leying zhang, Xiaofei Wang, Heng Lu, Manthan Thakker, Jinyu Li, sheng zhao, Zhizheng Wu

ICLR 2026 · Video › Video segmentation and tracking · approach: Learned video compression

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 changedWhereMeasuredEffect
replace DualCodec SSL feature (w2v-bert-2) with SenseVoice ASR feature (ablation)FlexiCodec-style codec at fixed 6.25Hz · LibriSpeech test-clean, RVQ1WER (%): 31.5 -> 5.99Improved
add dynamic frame rate merging (ablation)FlexiCodec with transformers and FSQ · LibriSpeech test-clean 6.25Hz, RVQ1WER (%): 5.22 -> 4.15Improved
add Merging and Unmerging transformers to fixed-rate codec (ablation)fixed-rate SenseVoice codec · 6.25Hz, RVQ1WER (%): 5.99 -> 5.40Improved
use FSQ instead of VQ for semantic tokens (ablation)FlexiCodec · 6.25Hz, RVQ1WER (%): 4.43 -> 4.15Improved
add Transformer to frame merging or unmerging modules (ablation)FlexiCodec · 6.25Hz acoustic testPESQ/UTMOS/SIM: PESQ 2.46 -> 2.76 (merging)Improved
use separate parameters for the two merging streams instead of shared (ablation)FlexiCodec frame merging · 6.25Hz, RVQ1WER (%): 8.24 -> 4.15Improved
use dynamic frame rate instead of fixed frame rate (ablation)FlexiCodec · 6.25Hz, RVQ1/ASR probing/RVQ1:8WER: relative 26% (RVQ-1), 21% (ASR probing), 8% (RVQ1:8)Improved
use dynamic frame rate instead of fixed frame rate (ablation)FlexiCodec · acoustic metrics (PESQ, UTMOS, MCD, SIM)PESQ/UTMOSNo clear effect
use Whisper-medium or averaged SenseVoice instead of last-layer SenseVoice-Small (ablation)FlexiCodec · 6.25Hz, RVQ1WER (%): 4.15 -> 9.83 (Whisper), 4.66 (avg SenseVoice)Hurt
use 12.5Hz NAR instead of 50Hz Mel NAR in TTS (ablation)FlexiCodec-TTS · LibriSpeech-PC test-cleanWER (%): 3.2 -> 4.6 at 6.25Hz ARHurt
lower AR frame rate from 12.5Hz to 6.25Hz with 50Hz NAR (ablation)FlexiCodec-TTS · LibriSpeech-PC test-cleanWER (%): 2.5 -> 3.2Mixed
lower frame rate of retrained codec from 12.5Hz to 6.25Hz (ablation)DualCodec · LibriSpeech test-clean, RVQ1WER (%): 5.93 -> 31.5Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy