ASR for Under-Resourced Languages From Probabilistic Transcription

• Published in: IEEE/ACM transactions on audio, speech, and language processing Vol. 25; no. 1; pp. 50 - 63
• Main Authors: Hasegawa-Johnson, Mark A., Jyothi, Preethi, McCloy, Daniel, Mirbagheri, Majid, Di Liberto, Giovanni M., Das, Amit, Ekin, Bradley, Chunxi Liu, Manohar, Vimal, Hao Tang, Lalor, Edmund C., Chen, Nancy F., Hager, Paul, Kekona, Tyler, Sloan, Rose, Lee, Adrian K. C.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01-01-2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Automatic speech recognition; Brain models; Coding; Crowdsourcing; EEG; Electroencephalography; Language modeling; Languages; mismatched crowdsourcing; Phonetic transcription; Probabilistic logic; Probabilistic methods; Speech; Speech perception; Speech processing; Speech recognition; under-resourced languages; Voice recognition
• ISSN: 2329-9290; 2329-9304
• DOI: 10.1109/TASLP.2016.2621659

In many under-resourced languages it is possible to find text, and it is possible to find speech, but transcribed speech suitable for training automatic speech recognition (ASR) is unavailable. In the absence of native transcripts, this paper proposes the use of a probabilistic transcript: A probability mass function over possible phonetic transcripts of the waveform. Three sources of probabilistic transcripts are demonstrated. First, self-training is a well-established semisupervised learning technique, in which a cross-lingual ASR first labels unlabeled speech, and is then adapted using the same labels. Second, mismatched crowdsourcing is a recent technique in which nonspeakers of the language are asked to write what they hear, and their nonsense transcripts are decoded using noisy channel models of second-language speech perception. Third, EEG distribution coding is a new technique in which nonspeakers of the language listen to it, and their electrocortical response signals are interpreted to indicate probabilities. ASR was trained in four languages without native transcripts. Adaptation using mismatched crowdsourcing significantly outperformed self-training, and both significantly outperformed a cross-lingual baseline. Both EEG distribution coding and text-derived phone language models were shown to improve the quality of probabilistic transcripts derived from mismatched crowdsourcing.