Statistical Transformation of Language and Pronunciation Models for Spontaneous Speech Recognition

• Published in: IEEE transactions on audio, speech, and language processing Vol. 18; no. 6; pp. 1539 - 1549
• Main Authors: Akita, Yuya, Kawahara, Tatsuya
• Format: Journal Article
• Language: English
• Published: Piscataway, NJ IEEE 01.08.2010; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Automatic speech recognition; Automatic speech recognition (ASR); Error analysis; Exact sciences and technology; Information, signal and communications theory; language model (LM); Minutes; Miscellaneous; Natural languages; Predictive models; Probability; pronunciation model; Signal processing; Speech processing; Speech recognition; spontaneous speech; statistical transformation; Statistics; Telecommunications and information theory; Telephony; Speech analysis; Automatic speech recognition (ASR); Archive; Pronunciation; Lexicon; Error rate; Mapping; Portability; pronunciation model; spontaneous speech; Modeling; statistical transformation; Language processing; Statistical model; Speech recognition; language model (LM); Automatic recognition; Speech processing
• ISSN: 1558-7916; 1558-7924
• DOI: 10.1109/TASL.2009.2037400

We propose a novel approach based on a statistical transformation framework for language and pronunciation modeling of spontaneous speech. Since it is not practical to train a spoken-style model using numerous spoken transcripts, the proposed approach generates a spoken-style model by transforming an orthographic model trained with document archives such as the minutes of meetings and the proceedings of lectures. The transformation is based on a statistical model estimated using a small amount of a parallel corpus, which consists of faithful transcripts aligned with their orthographic documents. Patterns of transformation, such as substitution, deletion, and insertion of words, are extracted with their word and part-of-speech (POS) contexts, and transformation probabilities are estimated based on occurrence statistics in a parallel aligned corpus. For pronunciation modeling, subword-based mapping between baseforms and surface forms is extracted with their occurrence counts, then a set of rewrite rules with their probabilities are derived as a transformation model. Spoken-style language and pronunciation (surface forms) models can be predicted by applying these transformation patterns to a document-style language model and baseforms in a lexicon, respectively. The transformed models significantly reduced perplexity and word error rates (WERs) in a task of transcribing congressional meetings, even though the domains and topics were different from the parallel corpus. This result demonstrates the generality and portability of the proposed framework.