Towards End-to-End Code-Switching Speech Recognition

Abstract

Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems considerably by predicting graphemes or characters directly from acoustic input. In the mean time, the need of expert linguistic knowledge is also eliminated, which makes it an attractive choice for code-switching ASR. This paper presents a hybrid CTC-Attention based end-to-end Mandarin-English code-switching (CS) speech recognition system and studies the effect of hybrid CTC-Attention based models, different modeling units, the inclusion of language identification and different decoding strategies on the task of code-switching ASR. On the SEAME corpus, our system achieves a mixed error rate (MER) of 34.24%.

5 pages, submitted to ICASSP 2019

References in corpus (5)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Towards better decoding and language model integration in sequence to sequence models
• A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese
• A comparable study of modeling units for end-to-end Mandarin speech recognition

Cited by in corpus (8)

• A Survey of Code-switched Speech and Language Processing
• Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
• Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition
• End-to-End ASR for Code-switched Hindi-English Speech
• Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition
• Investigations on Speech Recognition Systems for Low-Resource Dialectal Arabic-English Code-Switching Speech
• Multi-Modal Transformers Utterance-Level Code-Switching Detection
• Joint Language Identification of Code-Switching Speech using Attention based E2E Network