| DOI | Trouver le DOI : https://doi.org/10.1109/ICASSP49660.2025.10888920 |
|---|
| Auteur | Rechercher : Xu, Haoning; Rechercher : Li, Zhaoqing; Rechercher : Jin, Zengrui; Rechercher : Wang, Huimeng; Rechercher : Chen, Youjun; Rechercher : Li, Guinan; Rechercher : Geng, Mengzhe1; Rechercher : Hu, Shujie; Rechercher : Deng, Jiajun; Rechercher : Liu, Xunying |
|---|
| Affiliation | - Conseil national de recherches Canada. Technologies numériques
|
|---|
| Format | Texte, Article |
|---|
| Conférence | 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, April 6 - 11, 2025, Hyderabad, India |
|---|
| Sujet | low-bit quantization; mixed-precision quantization; speech foundation model |
|---|
| Résumé | This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models suggest the resulting mixed-precision quantized models increased the lossless compression ratio by factors up to 1.7x and 1.9x over the respective uniform-precision and two-stage mixed-precision quantized baselines that perform precision learning and model parameters quantization in separate and disjointed stages, while incurring no statistically word error rate (WER) increase over the 32-bit full-precision models. The system compression time of wav2vec2.0-base and HuBERT-large models is reduced by up to 1.9 and 1.5 times over the two-stage mixed-precision baselines, while both produce lower WERs. The best-performing 3.5-bit mixed-precision quantized HuBERT-large model produces a lossless compression ratio of 8.6x over the 32-bit full-precision system. |
|---|
| Date de publication | 2025-04-06 |
|---|
| Maison d’édition | IEEE |
|---|
| Dans | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Oui |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | 56faf904-e182-46a7-b427-7135c3d72b95 |
|---|
| Enregistrement créé | 2025-04-03 |
|---|
| Enregistrement modifié | 2025-04-08 |
|---|
