Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal Language Model Estimation

no code implementations • 5 May 2023 • Nilaksh Das, Monica Sunkara, Sravan Bodapati, Jinglun Cai, Devang Kulshreshtha, Jeff Farris, Katrin Kirchhoff

Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models such as attention-based encoder-decoder and RNN-T.

Decoder Domain Adaptation +1

Dynamic Chunk Convolution for Unified Streaming and Non-Streaming Conformer ASR

no code implementations • 18 Apr 2023 • Xilai Li, Goeric Huybrechts, Srikanth Ronanki, Jeff Farris, Sravan Bodapati

Overall, our proposed model reduces the degradation of the streaming mode over the non-streaming full-contextual model from 41. 7% and 45. 7% to 16. 7% and 26. 2% on the LibriSpeech test-clean and test-other datasets respectively, while improving by a relative 15. 5% WER over the previous state-of-the-art unified model.

speech-recognition Speech Recognition

Towards Personalization of CTC Speech Recognition Models with Contextual Adapters and Adaptive Boosting

no code implementations • 18 Oct 2022 • Saket Dingliwal, Monica Sunkara, Sravan Bodapati, Srikanth Ronanki, Jeff Farris, Katrin Kirchhoff

End-to-end speech recognition models trained using joint Connectionist Temporal Classification (CTC)-Attention loss have gained popularity recently.

Decoder speech-recognition +1