Toward Domain-invariant Speech Recognition Via Large Scale Training
2018 · Arun Narayanan, Ananya Misra, Khe Chai Sim, et al.
Abstract
Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the training domain, performance significantly drops. This work explores the idea of building a single domain-invariant model for varied use-cases by combining large scale training data from multiple application domains. Our final system is trained using 162,000 hours of speech. Additionally, each utterance is artificially distorted during training to simulate effects like background noise, codec distortion, and sampling rates. Our results show that, even at such a scale, a model thus trained works almost as well as those fine-tuned to specific subsets: A single model can be robust to multiple application domains, and variations like codecs and noise. More importantly, such models generalize better to unseen conditions and allow for rapid adaptation -- w
Authors
(none)
Tags
Stats
Related papers
- Adversarial Learning Of Raw Speech Features For Domain Invariant Speech Recognition (2018)9.23
- Adversarial Training For Multi-domain Speaker Recognition (2020)6.77
- Extracting Domain Invariant Features By Unsupervised Learning For Robust Automatic Speech Recognition (2018)9.03
- Bigssl: Exploring The Frontier Of Large-scale Semi-supervised Learning For Automatic Speech Recognition (2021)15.73
- Large-scale Domain Adaptation Via Teacher-student Learning (2017)13.93
- Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23
- Multi-staged Cross-lingual Acoustic Model Adaption For Robust Speech Recognition In Real-world Applications -- A Case Study On German Oral History Interviews (2020)0.00
- Large-scale Learning Of Generalised Representations For Speaker Recognition (2022)0.00