2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
| Paper ID | SPE-27.2 | ||
| Paper Title | BLSTM-BASED CONFIDENCE ESTIMATION FOR END-TO-END SPEECH RECOGNITION | ||
| Authors | Atsunori Ogawa, Naohiro Tawara, Takatomo Kano, Marc Delcroix, NTT Corporation, Japan | ||
| Session | SPE-27: Speech Recognition 9: Confidence Measures | ||
| Location | Gather.Town | ||
| Session Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
| Presentation Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
| Presentation | Poster | ||
| Topic | Speech Processing: [SPE-GASR] General Topics in Speech Recognition | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Confidence estimation, in which we estimate the reliability of each recognized token (e.g., word, sub-word, and character) in automatic speech recognition (ASR) hypotheses and detect incorrectly recognized tokens, is an important function for developing ASR applications. In this study, we perform confidence estimation for end-to-end (E2E) ASR hypotheses. Recent E2E ASR systems show high performance (e.g., around 5% token error rates) for various ASR tasks. In such situations, confidence estimation becomes difficult since we need to detect infrequent incorrect tokens from mostly correct token sequences. To tackle this imbalanced dataset problem, we employ a bidirectional long short-term memory (BLSTM)-based model as a strong binary-class (correct/incorrect) sequence labeler that is trained with a class balancing objective. We experimentally confirmed that, by utilizing several types of ASR decoding scores as its auxiliary features, the model steadily shows high confidence estimation performance under highly imbalanced settings. We also confirmed that the BLSTM-based model outperforms Transformer-based confidence estimation models, which greatly underestimate incorrect tokens. | ||