Litcius/Paper detail

On Addressing Practical Challenges for RNN-Transducer

Rui Zhao, Jian Xue, Jinyu Li, Wenning Wei, Lei He, Yifan Gong

20212021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)19 citationsDOI

Abstract

In this paper, several works are proposed to address practi-cal challenges for deploying RNN Transducer (RNN-T) based speech recognition systems. These challenges are adapting a well-trained RNN-T model to a new domain without col-lecting the audio data, obtaining time stamps and confidence scores at word level. We solve the first challenge with a splicing data method which concatenates the speech segments ex-tracted from the source domain data. To get time stamps, a phone prediction branch is added to the RNN-T model by sharing the encoder for the purpose of forced alignment. Fi-nally, we obtain word level confidence scores by utilizing sev-eral types of features calculated during decoding and from a confusion network. Evaluated with Microsoft production data, the splicing data adaptation method improves the base-line and adaptation with the text to speech method by 58.03% and 15.25% relative word error rate reduction, respectively. The proposed time stamping method can get less than 50 mil-lisecond word timing difference from the ground truth align-ment on average while maintaining the recognition accuracy. We also obtain high confidence annotation performance with limited computation cost.

Topics & Concepts

Computer scienceSpeech recognitionWord error rateWord (group theory)PhoneEncoderArtificial intelligenceOperating systemLinguisticsPhilosophySpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing