A Comparative Analysis Between Conformer-transducer, Whisper, And Wav2vec2 For Improving The Child Speech Recognition
2023 · Andrei Barcovschi, Rishabh Jain, Peter Corcoran
Abstract
Automatic Speech Recognition (ASR) systems have progressed significantly in their performance on adult speech data; however, transcribing child speech remains challenging due to the acoustic differences in the characteristics of child and adult voices. This work aims to explore the potential of adapting state-of-the-art Conformer-transducer models to child speech to improve child speech recognition performance. Furthermore, the results are compared with those of self-supervised wav2vec2 models and semi-supervised multi-domain Whisper models that were previously finetuned on the same data. We demonstrate that finetuning Conformer-transducer models on child speech yields significant improvements in ASR performance on child speech, compared to the non-finetuned models. We also show Whisper and wav2vec2 adaptation on different child speech datasets. Our detailed comparative analysis shows that wav2vec2 provides the most consistent performance improvements among the three methods studied.
Authors
(none)
Tags
Stats
Related papers
- Improving Child Speech Recognition With Augmented Child-like Speech (2024)5.24
- An Investigation On Applying Acoustic Feature Conversion To ASR Of Adult And Child Speech (2022)0.00
- Benchmarking Children's ASR With Supervised And Self-supervised Speech Foundation Models (2024)8.60
- Whisper Turns Stronger: Augmenting Wav2vec 2.0 For Superior ASR In Low-resource Languages (2024)0.00
- Transfer Learning For Robust Low-resource Children's Speech ASR With Transformers And Source-filter Warping (2022)6.77
- Examining Test-time Adaptation For Personalized Child Speech Recognition (2024)0.00
- On The Transferability Of Whisper-based Representations For "in-the-wild" Cross-task Downstream Speech Applications (2023)0.00
- Towards A Unified Conformer Structure: From ASR To ASV Task (2022)13.11