DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation

Abstract

In previous works, only parameter weights of ASR models are optimized under fixed-topology architecture. However, the design of successful model architecture has always relied on human experience and intuition. Besides, many hyperparameters related to model architecture need to be manually tuned. Therefore in this paper, we propose an ASR approach with efficient gradient-based architecture search, DARTS-ASR. In order to examine the generalizability of DARTS-ASR, we apply our approach not only on many languages to perform monolingual ASR, but also on a multilingual ASR setting. Following previous works, we conducted experiments on a multilingual dataset, IARPA BABEL. The experiment results show that our approach outperformed the baseline fixed-topology architecture by 10.2% and 10.0% relative reduction on character error rates under monolingual and multilingual ASR settings respectively. Furthermore, we perform some analysis on the searched architectures by DARTS-ASR.

arXiv commentAccepted at INTERSPEECH 2020

References in corpus (4)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• DARTS: Differentiable Architecture Search
• Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model
• Leveraging End-to-End Speech Recognition with Neural Architecture Search

Cited by in corpus (5)

• Multilingual and code-switching ASR challenges for low resource Indian languages
• AutoKWS: Keyword Spotting with Differentiable Architecture Search
• Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients
• Multi-accent Speech Separation with One Shot Learning
• Latency-Controlled Neural Architecture Search for Streaming Speech Recognition