One-pass Multiple Conformer And Foundation Speech Systems Compression And Quantization Using An All-in-one Neural Model

Abstract

We propose a novel one-pass multiple ASR systems joint compression and quantization approach using an all-in-one neural model. A single compression cycle allows multiple nested systems with varying Encoder depths, widths, and quantization precision settings to be simultaneously constructed without the need to train and store individual target systems separately. Experiments consistently demonstrate the multiple ASR systems compressed in a single all-in-one model produced a word error rate (WER) comparable to, or lower by up to 1.01% absolute (6.98% relative) than individually trained systems of equal complexity. A 3.4x overall system compression and training time speed-up was achieved. Maximum model size compression ratios of 12.8x and 3.93x were obtained over the baseline Switchboard-300hr Conformer and LibriSpeech-100hr fine-tuned wav2vec2.0 models, respectively, incurring no statistically significant WER increase.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2024one

Related papers

• Empirical Evaluation Of Deep Learning Model Compression Techniques On The Wavenet Vocoder (2020)0.00
• Accurate And Structured Pruning For Efficient Automatic Speech Recognition (2023)7.81
• Usm-lite: Quantization And Sparsity Aware Fine-tuning For Speech Recognition With Universal Speech Models (2023)4.52
• CQNV: A Combination Of Coarsely Quantized Bitstream And Neural Vocoder For Low Rate Speech Coding (2023)6.34
• Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies Of Large End-to-end Models (2024)5.84
• Optimization Of Dnn-based Speaker Verification Model Through Efficient Quantization Technique (2024)0.00
• Optimizing Neural Speech Codec For Low-bitrate Compression Via Multi-scale Encoding (2024)0.00
• 3M: Multi-loss, Multi-path And Multi-level Neural Networks For Speech Recognition (2022)8.67