Focused Discriminative Training For Streaming Ctc-trained Automatic Speech Recognition Models

Abstract

This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of CTC and attention-based encoder-decoder (AED) loss. The proposed approach presents a novel framework to identify and improve a model's recognition on challenging segments of an audio. Notably, this training framework is independent of hidden Markov models (HMMs) and lattices, eliminating the need for substantial decision-making regarding HMM topology, lexicon, and graph generation, as typically required in standard discriminative training approaches. Compared to additional fine-tuning with MMI or MWER loss on the encoder, FDT is shown to be more effective in achieving greater reductions in Word Error Rate (WER) on streaming models trained on LibriSpeech. Additionally, this method is shown to be effective in further improving a converged word-piece s

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhaider2024focused

Related papers

• Mask-ctc-based Encoder Pre-training For Streaming End-to-end Speech Recognition (2023)0.00
• Alignment Knowledge Distillation For Online Streaming Attention-based Speech Recognition (2021)7.16
• An Investigation Of Enhancing CTC Model For Triggered Attention-based Streaming ASR (2021)0.00
• Bridging The Gap Between Streaming And Non-streaming ASR Systems Bydistilling Ensembles Of CTC And RNN-T Models (2021)3.58
• Dynamic Latency For Ctc-based Streaming Automatic Speech Recognition With Emformer (2022)0.00
• Unified Streaming And Non-streaming Two-pass End-to-end Model For Speech Recognition (2020)0.00
• WNARS: WFST Based Non-autoregressive Streaming End-to-end Speech Recognition (2021)0.00
• Improved Training For End-to-end Streaming Automatic Speech Recognition Model With Punctuation (2023)0.00