Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Junyi, Zhang, Chi, Qian, Jing, Luo, Haifeng, Wang, Hao, Jin, Zengrui, Zhang, Chao
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.14654
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910145574862848
author Wang, Junyi
Zhang, Chi
Qian, Jing
Luo, Haifeng
Wang, Hao
Jin, Zengrui
Zhang, Chao
author_facet Wang, Junyi
Zhang, Chi
Qian, Jing
Luo, Haifeng
Wang, Hao
Jin, Zengrui
Zhang, Chao
contents In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 200 bit per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 3.68% WER on the LibriSpeech test-clean set at 200 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.20% on test-clean and 8.93% on test-other, corresponding to a 13% relative reduction while preserving perceptual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14654
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ClariCodec: Optimising Neural Speech Codes for 200bps Communication using Reinforcement Learning
Wang, Junyi
Zhang, Chi
Qian, Jing
Luo, Haifeng
Wang, Hao
Jin, Zengrui
Zhang, Chao
Sound
Audio and Speech Processing
In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 200 bit per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 3.68% WER on the LibriSpeech test-clean set at 200 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.20% on test-clean and 8.93% on test-other, corresponding to a 13% relative reduction while preserving perceptual quality.
title ClariCodec: Optimising Neural Speech Codes for 200bps Communication using Reinforcement Learning
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2604.14654