Minimum Bayes Risk Training For End-to-end Speaker-attributed ASR

Abstract

Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous study, the model parameters were trained based on the speaker-attributed maximum mutual information (SA-MMI) criterion, with which the joint posterior probability for multi-talker transcription and speaker identification are maximized over training data. Although SA-MMI training showed promising results for overlapped speech consisting of various numbers of speakers, the training criterion was not directly linked to the final evaluation metric, i.e., speaker-attributed word error rate (SA-WER). In this paper, we propose a speaker-attributed minimum Bayes risk (SA-MBR) training method where the parameters are trained to directly minimize the expected SA-WER over the training data. Experiments using the LibriSpeech corpus show that the proposed SA-MBR trai

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykanda2020minimum

Related papers

• Investigation Of End-to-end Speaker-attributed ASR For Continuous Multi-talker Recordings (2020)10.35
• Minimum Bayes Risk Training Of Rnn-transducer For End-to-end Speech Recognition (2019)0.00
• Minimum Word Error Rate Training For Attention-based Sequence-to-sequence Models (2017)14.35
• A Comparative Study Of Modular And Joint Approaches For Speaker-attributed ASR On Monaural Long-form Audio (2021)7.50
• Auxiliary Interference Speaker Loss For Target-speaker Speech Recognition (2019)9.76
• MSA-ASR: Efficient Multilingual Speaker Attribution With Frozen ASR Models (2024)2.26
• Hypothesis Stitcher For End-to-end Speaker-attributed ASR On Long-form Multi-talker Recordings (2021)5.24
• Improving Speaker Assignment In Speaker-attributed ASR For Real Meeting Applications (2024)0.00