RNN-Transducer-based Losses for Speech Recognition on Noisy Targets
Training speech recognition systems on noisy transcripts is a significant challenge in industrial pipelines, where datasets are enormous and ensuring accurate transcription for every instance is difficult. In this work, we introduce novel loss functions to mitigate the impact of transcription errors in RNN-Transducer models. Our Star-Transducer loss addresses deletion errors by incorporating "skip frame" transitions in the loss lattice, restoring over 90% of the system's performance compared to models trained with accurate transcripts. The Bypass-Transducer loss uses "skip token" transitions to tackle insertion errors, recovering more than 60% of the quality. Finally, the Target-Robust Transducer loss merges these approaches, offering robust performance against arbitrary errors. Experimental results demonstrate that the Target-Robust Transducer loss significantly improves RNN-T performance on noisy data by restoring over 70% of the quality compared to well-transcribed data.
Code (1)
Tasks
speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
This paper proposes a new approach to perform unsupervised fine-tuning and self-training using unlabeled speech data for recurrent neural network (RNN)-Transducer (RNN-T) end-to-end (E2E) automatic speech recognition (AS…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionMemory-Efficient Training of RNN-Transducer with Sampled Softmax
RNN-Transducer has been one of promising architectures for end-to-end automatic speech recognition. Although RNN-Transducer has many advantages including its strong accuracy and streaming-friendly property, its high memo…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSequence Transduction with Graph-based Supervision
The recurrent neural network transducer (RNN-T) objective plays a major role in building today's best automatic speech recognition (ASR) systems for production. Similarly to the connectionist temporal classification (CTC…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionInput Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
End-to-end models have achieved state-of-the-art results on several automatic speech recognition tasks. However, they perform poorly when evaluated on long-form data, e.g., minutes long conversational telephony audio. On…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Formspeech-recognition+1Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses
Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabele…
Automatic Speech Recognitionspeech-recognitionSpeech Recognition