Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders
Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output. However, these models are tightly coupled with speech content, and produce unintended outputs in noisy conditions. Based on VQ-VAE autoencoders with WaveRNN decoders, we develop compressor-enhancer encoders and accompanying decoders, and show that they operate well in noisy conditions. We also observe that a compressor-enhancer model performs better on clean speech inputs than a compressor model trained only on clean speech.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker ver…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)QuantizationSpeaker Verification+2CleanCodec: 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 effic…
Voice ConversionProbing the Robustness Properties of Neural Speech Codecs
Neural speech codecs have revolutionized speech coding, achieving higher compression while preserving audio fidelity. Beyond compression, they have emerged as tokenization strategies, enabling language modeling on speech…
Language ModelingLanguage ModellingVision-Integrated High-Quality Neural Speech Coding
This paper proposes a novel vision-integrated neural speech codec (VNSC), which aims to enhance speech coding quality by leveraging visual modality information. In VNSC, the image analysis-synthesis module extracts visua…
Baseline Systems For The 2025 Low-Resource Audio Codec Challenge
The Low-Resource Audio Codec (LRAC) Challenge aims to advance neural audio coding for deployment in resource-constrained environments. The first edition focuses on low-resource neural speech codecs that must operate reli…