Interspeech 2022 · 2022 · 10 citations · 37 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingLanguage ModelingSpeech RecognitionSpoken CorporaCross-lingual TransferCross-lingual Transfer LearningLow-resource Speech RecognitionPhoneme RecognitionPhoneme-to-acoustics MappingRead SpeechSemi-supervised ModelsZero-shot Cross-lingual Transfer
We present a method for cross-lingual training an ASR system using absolutely no transcribed training data from the target language, and with no phonetic knowledge of the language in question. Our approach uses a novel application of a decipherment algorithm, which operates given only unpaired speech and text data from the target language. We apply this decipherment to phone sequences generated by a universal phone recogniser trained on out-of-language speech corpora, which we follow with flat-start semi-supervised training to obtain an acoustic model for the new language. To the best of our knowledge, this is the first practical approach to zero-resource cross-lingual ASR which does not rely on any hand-crafted phonetic information. We carry out experiments on read speech from the GlobalPhone corpus, and show that it is possible to learn a decipherment model on just 20 minutes of data from the target language. When used to generate pseudo-labels for semi-supervised training, we obtain WERs that range from 32.5% to just 1.9% absolute worse than the equivalent fully supervised models trained on the same data.
37
Librispeech: An ASR corpus based on public domain audio books
Vassil Panayotov, Guoguo Chen, Daniel Povey et al. · 2015 · 6K citations
Computing, Computer Science, English +17
Kaldi Speech Recognition Toolkit
Daniel Povey · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2024 · 4.9K citations · Full text
Computing, Linguistics, Acoustics +15
SRILM - an extensible language modeling toolkit
Andreas Stolcke · 2002 · 4.4K citations