Pre-Finetuning for Few-Shot Emotional Speech Recognition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Maximillian, Yu, Zhou
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915008250642432
author Chen, Maximillian
Yu, Zhou
author_facet Chen, Maximillian
Yu, Zhou
contents Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production environments. We view speaker adaptation as a few-shot learning problem and propose investigating transfer learning approaches inspired by recent success with pre-trained models in natural language tasks. We propose pre-finetuning speech models on difficult tasks to distill knowledge into few-shot downstream classification objectives. We pre-finetune Wav2Vec2.0 on every permutation of four multiclass emotional speech recognition corpora and evaluate our pre-finetuned models through 33,600 few-shot fine-tuning trials on the Emotional Speech Dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2302_12921
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pre-Finetuning for Few-Shot Emotional Speech Recognition
Chen, Maximillian
Yu, Zhou
Computation and Language
Machine Learning
Sound
Audio and Speech Processing
Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production environments. We view speaker adaptation as a few-shot learning problem and propose investigating transfer learning approaches inspired by recent success with pre-trained models in natural language tasks. We propose pre-finetuning speech models on difficult tasks to distill knowledge into few-shot downstream classification objectives. We pre-finetune Wav2Vec2.0 on every permutation of four multiclass emotional speech recognition corpora and evaluate our pre-finetuned models through 33,600 few-shot fine-tuning trials on the Emotional Speech Dataset.
title Pre-Finetuning for Few-Shot Emotional Speech Recognition
topic Computation and Language
Machine Learning
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2302.12921