Acquiring Pronunciation Knowledge From Transcribed Speech Audio Via Multi-task Learning

Abstract

Recent work has shown the feasibility and benefit of bootstrapping an integrated sequence-to-sequence (Seq2Seq) linguistic frontend from a traditional pipeline-based frontend for text-to-speech (TTS). To overcome the fixed lexical coverage of bootstrapping training data, previous work has proposed to leverage easily accessible transcribed speech audio as an additional training source for acquiring novel pronunciation knowledge for uncovered words, which relies on an auxiliary ASR model as part of a cumbersome implementation flow. In this work, we propose an alternative method to leverage transcribed speech audio as an additional training source, based on multi-task learning (MTL). Experiments show that, compared to a baseline Seq2Seq frontend, the proposed MTL-based method reduces PER from 2.5% to 1.6% for those word types covered exclusively in transcribed speech audio, achieving a similar performance to the previous method but with a much simpler implementation flow.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysun2024acquiring

Related papers

• On The Inductive Bias Of Word-character-level Multi-task Learning For Speech Recognition (2018)0.00
• Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition (2017)0.00
• Improving Sequence-to-sequence Acoustic Modeling By Adding Text-supervision (2018)9.92
• Bootstrap An End-to-end ASR System By Multilingual Training, Transfer Learning, Text-to-text Mapping And Synthetic Audio (2020)5.24
• Prior-agnostic Multi-scale Contrastive Text-audio Pre-training For Parallelized TTS Frontend Modeling (2024)0.00
• Accent-robust Automatic Speech Recognition Using Supervised And Unsupervised Wav2vec Embeddings (2021)0.00
• A General Multi-task Learning Framework To Leverage Text Data For Speech To Text Tasks (2020)11.67
• Towards Lifelong Learning Of Multilingual Text-to-speech Synthesis (2021)3.58