End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations

Abstract

Conventional keyword search systems operate on automatic speech recognition (ASR) outputs, which causes them to have a complex indexing and search pipeline. This has led to interest in ASR-free approaches to simplify the search procedure. We recently proposed a neural ASR-free keyword search model which achieves competitive performance while maintaining an efficient and simplified pipeline, where queries and documents are encoded with a pair of recurrent neural network encoders and the encodings are combined with a dot-product. In this article, we extend this work with multilingual pretraining and detailed analysis of the model. Our experiments show that the proposed multilingual training significantly improves the model performance and that despite not matching a strong ASR-based conventional keyword search system for short queries and queries comprising in-vocabulary words, the proposed model outperforms the ASR-based system for long queries and queries that do not appear in the training data.

arXiv commentAccepted by IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 2023

References in corpus (8)

• Libri-Light: A Benchmark for ASR with Limited or No Supervision
• TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
• Improving language models by retrieving from trillions of tokens
• Self-Training for End-to-End Speech Recognition
• End-to-End ASR-free Keyword Search from Speech
• Spoken Term Detection and Relevance Score Estimation using Dot-Product of Pronunciation Embeddings
• Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer
• End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations

Cited by in corpus (1)

• End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations