Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers

no code implementations • 2 Nov 2022 • Duc Le, Frank Seide, Yuhao Wang, Yang Li, Kjell Schubert, Ozlem Kalinli, Michael L. Seltzer

We show how factoring the RNN-T's output distribution can significantly reduce the computation cost and power consumption for on-device ASR inference with no loss in accuracy.

Improving Data Driven Inverse Text Normalization using Data Augmentation

no code implementations • 20 Jul 2022 • Laxmi Pandey, Debjyoti Paul, Pooja Chitkara, Yutong Pang, Xuedong Zhang, Kjell Schubert, Mark Chou, Shu Liu, Yatharth Saraf

Inverse text normalization (ITN) is used to convert the spoken form output of an automatic speech recognition (ASR) system to a written form.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR

no code implementations • 9 Nov 2020 • Xiaohui Zhang, Frank Zhang, Chunxi Liu, Kjell Schubert, Julian Chan, Pradyot Prakash, Jun Liu, Ching-Feng Yeh, Fuchun Peng, Yatharth Saraf, Geoffrey Zweig

In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

RNN-T For Latency Controlled ASR With Improved Beam Search

no code implementations • 5 Nov 2019 • Mahaveer Jain, Kjell Schubert, Jay Mahadeokar, Ching-Feng Yeh, Kaustubh Kalgaonkar, Anuroop Sriram, Christian Fuegen, Michael L. Seltzer

Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic model, language model, punctuation model, inverse text normalization) into one single model.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Transformer-Transducer: End-to-End Speech Recognition with Self-Attention

1 code implementation • 28 Oct 2019 • Ching-Feng Yeh, Jay Mahadeokar, Kaustubh Kalgaonkar, Yongqiang Wang, Duc Le, Mahaveer Jain, Kjell Schubert, Christian Fuegen, Michael L. Seltzer

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition.

speech-recognition Speech Recognition