BridgeCodec: Mamba Enhanced Neural Audio Codec with Schrödinger Bridge at Low Bitrate

Zijian Lin; Jing Yang; Jinghao Luo; Zhuo Wang; Fan Fan; Zhiyong Wu

cs.SDOct 11, 2026

BridgeCodec: Mamba Enhanced Neural Audio Codec with Schrödinger Bridge at Low Bitrate

Authors: Zijian Lin, Jing Yang, Jinghao Luo, Zhuo Wang, Fan Fan, Zhiyong Wu

Organizations: Shenzhen International Graduate School, Tsinghua University, China · Central Media Technology Institute, Huawei

Abstract

Neural audio codecs achieve remarkable performance but operate as closed ecosystems with rigidly co-trained encoderdecoder pairs, severely hindering interoperability. To resolve this, we propose BridgeCodec, a versatile framework that decouples these pairs by translating latent representations between mismatched, frozen endpoints. We formulate this cross-codec translation as a Schrödinger Bridge optimal transport problem, enabling robust mapping between disparate distributions without predefined noise priors. To efficiently capture longrange speech temporal dependencies, we integrate a Mambaenhanced U-Net architecture. We validate BridgeCodec on an extreme deployment scenario: mapping a lightweight 8 kHz source encoder directly to a 48 kHz target decoder at an ultralow bitrate of 1 kbps. Experimental results demonstrate that BridgeCodec achieves superior wideband reconstruction and high perceptual quality, successfully bridging heavily bottlenecked, heterogeneous codecs.

Figures & tables

Figure 1: The BridgeCodec framework consists of $\text{En}^{s}(\cdot)$ , Mamba-enhanced backbone, and $\text{De}^{t}(\cdot)$ . The source codec is marked with straight lines and the target codec with wavy lines, indicating they can use different model architectures and quantization methods.

Model	STOI $\uparrow$	STFT $\downarrow$	MEL $\downarrow$	DNSMOS $\uparrow$	WER $\downarrow$	SIM $\uparrow$	MOS $\uparrow$
target codec	0.96	1.63	1.05	3.26	1.70	0.99	4.24 $\pm$ 0.10
source codec	0.23	12.24	10.01	3.11	1.92	0.81	3.80 $\pm$ 0.11
BridgeCodec ${}_{\text{UNet}}$	0.86	2.27	1.74	3.09	2.16	0.93	-
BridgeCodec	0.88	2.22	1.65	3.17	2.11	0.96	4.12 $\pm$ 0.11
w/o Two stage training	0.87	2.19	1.68	3.15	2.04	0.95	-

Table 1: Main results of BridgeCodec on the testset. All audio is resampled to 48 kHz for STOI, STFT and MEL. And due to evaluation model constraints, all audio is resampled to 16 kHz for DNSMOS, WER and SIM. MOS represents the subjective Mean Opinion Score for naturalness and speech quality with 95% confidence intervals.

NFE	STOI	STFT	MEL	DNSMOS	WER	SIM
10	0.88	2.22	1.65	3.17	2.11	0.96
5	0.88	2.16	1.63	3.17	2.37	0.95
1	0.89	2.13	1.58	3.18	2.39	0.95

Table 2: The results with different number of function evaluations.

Neural Audio Codecs

Neural audio codecs learn compact representations for compressing and reconstructing speech, music, and other sounds.

See all 87 papers

CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space
Mar 2, 2026Bowen Zhang, Junchuan Zhao, Ian McLoughlin +2Speech Enhancement Neural Audio Codecs
Singapore Institute of Technology, Singapore · Nanyang Technological University, Singapore · National University of Singapore, Singapore
ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding
Sep 10, 2026Luca Della Libera, Cem Subakan, Mirco RavanelliAudio Token Compression Neural Audio Codecs
Concordia University · Mila-Quebec AI Institute · Universit´e Laval
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
Mar 6, 2026Junhyeok Lee, Xiluo He, Jihwan Lee +6Neural Audio Codecs Self-Supervised Learning
Center for Language and Speech Processing, Johns Hopkins University, USA · Signal Analysis and Interpretation Laboratory, University of Southern California, USA

Mar 2, 2026J/K move · Enter open · S save

CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space

Bowen Zhang, Junchuan Zhao, Ian McLoughlin, Ye Wang+1

Singapore Institute of Technology, Singapore · Nanyang Technological University, Singapore · National University of Singapore, Singapore

Speech Enhancement Neural Audio Codecs

Open paper AskPDF arXiv

Speech Bandwidth Extension improves clarity and intelligibility by restoring/inferring appropriate high-frequency content for low-bandwidth speech. Existing methods often rely on spectrogram or waveform modeling, which can incur higher computational cost and have limited high-frequency fidelity. Neural audio codecs offer compact latent representations that better preserve acoustic detail, yet accurately recovering high-resolution latent information remains challenging due to representation mismatch. We present CodecFlow, a neural codec-based BWE framework that performs efficient speech reconstruction in a compact latent space. CodecFlow employs a voicing-aware conditional flow converter on continuous codec embeddings and a structure-constrained residual vector quantizer to improve latent alignment stability. Optimized end-to-end, CodecFlow achieves strong spectral fidelity and enhanced perceptual quality on 8 kHz to 16 kHz and 44.1 kHz speech BWE tasks.

Abstract

Neural Audio Codecs

Explore similar work

CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space

ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding

Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec