Iterative Pseudo-Labeling for Speech Recognition
Autor: | Jacob Kahn, Gabriel Synnaeve, Tatiana Likhomanenko, Qiantong Xu, Ronan Collobert, Awni Hannun |
---|---|
Rok vydání: | 2020 |
Předmět: |
FOS: Computer and information sciences
Text corpus Sound (cs.SD) Computer Science - Computation and Language Computer science Speech recognition Acoustic model Computer Science - Sound 030507 speech-language pathology & audiology 03 medical and health sciences ComputingMethodologies_PATTERNRECOGNITION Audio and Speech Processing (eess.AS) FOS: Electrical engineering electronic engineering information engineering Labeled data Language model 0305 other medical science Computation and Language (cs.CL) Decoding methods Electrical Engineering and Systems Science - Audio and Speech Processing |
Zdroj: | INTERSPEECH |
Popis: | Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently performs multiple iterations of pseudo-labeling on unlabeled data as the acoustic model evolves. In particular, IPL fine-tunes an existing model at each iteration using both labeled data and a subset of unlabeled data. We study the main components of IPL: decoding with a language model and data augmentation. We then demonstrate the effectiveness of IPL by achieving state-of-the-art word-error rate on the Librispeech test sets in both standard and low-resource setting. We also study the effect of language models trained on different corpora to show IPL can effectively utilize additional text. Finally, we release a new large in-domain text corpus which does not overlap with the Librispeech training transcriptions to foster research in low-resource, semi-supervised ASR Comment: INTERSPEECH 2020 |
Databáze: | OpenAIRE |
Externí odkaz: |