Sequence-to-sequence ASR Optimization Via Reinforcement Learning

Abstract

Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch between the training and inference conditions. In the sequence-to-sequence architecture, the model is trained to predict the grapheme of the current time-step given the input of speech signal and the ground-truth grapheme history of the previous time-steps. However, it remains unclear how well the model approximates real-world speech during inference. Thus, generating the whole transcription from scratch based on previous predictions is complicated and errors can propagate over time. Furthermore, the model is optimized to maximize the likelihood of training data instead of error rate evaluation metrics that actually quantify recognition quality. This paper presents an alternative strategy for training sequence-to-sequence ASR models by adopting the idea of reinforcement learning (RL). Unlike the standard training

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keytjandra2017sequence

Related papers

• Incremental Text To Speech For Neural Sequence-to-sequence Models Using Reinforcement Learning (2020)5.24
• State-of-the-art Speech Recognition With Sequence-to-sequence Models (2017)21.01
• Shrinkml: End-to-end ASR Model Compression Using Reinforcement Learning (2019)9.41
• Reinforcement Learning Based Speech Enhancement For Robust Speech Recognition (2018)11.08
• ASRRL-TTS: Agile Speaker Representation Reinforcement Learning For Text-to-speech Speaker Adaptation (2024)0.00
• Speech Recognition With Llms Adapted To Disordered Speech Using Reinforcement Learning (2024)5.24
• Do As I Mean, Not As I Say: Sequence Loss Training For Spoken Language Understanding (2021)6.77
• Multilingual Sequence-to-sequence Speech Recognition: Architecture, Transfer Learning, And Language Modeling (2018)13.84