Coded Speech Enhancement Using Neural Network-Based Vector-Quantized Residual Features

Cheon, Youngju; Hwang, Soojoong; Han, Sang-Wook; Jang, Inseon; Shin, Jong Won

doi:10.21437/interspeech.2021-1204

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we combine the merit from both FP-and BP-QAT and propose General Quantizer (GQ) that navigates weights to quantization centroids without introducing augmented regularizers but via feedforward-only operators. Our work is inspired by a continuous relaxation of quantization [25] also used for speech representation learning [26,27,28,29,30,31,32], and µ-Law algorithm for 8-bit pulse-code modulation (PCM) digital telecommunication [33].…”

Section: Related Qat Approachesmentioning

confidence: 99%

Sub-8-bit quantization for on-device speech recognition: a regularization-free approach

Zhang¹,

Radfar²,

Nguyen³

et al. 2022

Preprint

View full text Add to dashboard Cite

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the quantization centroids have to be predetermined and fixed. To overcome this limitation, we introduce a regularization-free, "soft-to-hard" compression mechanism with self-adjustable centroids in a µ-Law constrained space, resulting in a simpler yet more versatile quantization scheme, called General Quantizer (GQ). We apply GQ to ASR tasks using Recurrent Neural Network Transducer (RNN-T) and Conformer architectures on both LibriSpeech and de-identified far-field datasets. Without accuracy degradation, GQ can compress both RNN-T and Conformer into sub-8-bit, and for some RNN-T layers, to 1-bit for fast and accurate inference. We observe a 30.73% memory footprint saving and 31.75% user-perceived latency reduction compared to 8-bit QAT via physical device benchmarking.

show abstract