| Download | - View final version: One-pass multiple conformer and foundation speech systems compression and quantization using an all-in-one neural model (PDF, 541 KiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.21437/Interspeech.2024-703 |
|---|
| Author | Search for: Li, Zhaoqing; Search for: Xu, Haoning; Search for: Wang, Tianzi; Search for: Hu, Shoukang; Search for: Jin, Zengrui; Search for: Hu, Shujie; Search for: Deng, Jiajun; Search for: Cui, Mingyu; Search for: Geng, Mengzhe1; Search for: Liu, Xunying |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | Interspeech 2024, September 1 - 5, 2024, Kos, Greece |
|---|
| Subject | ASR; model compression; model quantization; self-supervised learning; knowledge distillation; transformer |
|---|
| 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. |
|---|
| Publication date | 2024-09-01 |
|---|
| Publisher | ISCA |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | a290e7ac-4bb1-406d-9936-a996cb5b4729 |
|---|
| Record created | 2025-04-10 |
|---|
| Record modified | 2025-04-15 |
|---|
