Enhancing Into The Codec: Noise Robust Speech Coding With Vector-quantized Autoencoders

Abstract

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.

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keycasebeer2021enhancing

Related papers

• NDVQ: Robust Neural Audio Codec With Normal Distribution-based Vector Quantization (2024)0.00
• Variable Bitrate Residual Vector Quantization For Audio Coding (2024)3.58
• ERVQ: Enhanced Residual Vector Quantization With Intra-and-inter-codebook Optimization For Neural Audio Codecs (2024)6.34
• A Neural Speech Codec For Noise Robust Speech Coding (2023)0.00
• ESC: Efficient Speech Coding With Cross-scale Residual Vector Quantized Transformers (2024)5.84
• Low Bit-rate Speech Coding With VQ-VAE And A Wavenet Decoder (2019)14.80
• Latent-domain Predictive Neural Speech Coding (2022)12.15
• Deep Vocoder: Low Bit Rate Compression Of Speech With Deep Autoencoder (2019)5.24