Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units

Spiess T, Wrede B, Kummert F, Fink GA. Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units. In: Proc. European Conf. on Speech Communication and Technology. Geneva; 2003: 2549-2552.

Spiess, T., Wrede, B., Kummert, F., & Fink, G. A. (2003). Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units. Proc. European Conf. on Speech Communication and Technology, 2549-2552

Spiess, T., Wrede, B., Kummert, F., and Fink, G. A. (2003). “Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units” in Proc. European Conf. on Speech Communication and Technology (Geneva), 2549-2552.

Spiess, T., et al., 2003. Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units. In Proc. European Conf. on Speech Communication and Technology. Geneva, pp. 2549-2552.

T. Spiess, et al., “Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units”, Proc. European Conf. on Speech Communication and Technology, Geneva: 2003, pp.2549-2552.

Spiess, T., Wrede, B., Kummert, F., Fink, G.A.: Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units. Proc. European Conf. on Speech Communication and Technology. p. 2549-2552. Geneva (2003).

Spiess, Thurid, Wrede, Britta, Kummert, Franz, and Fink, Gernot A. “Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units”. Proc. European Conf. on Speech Communication and Technology. Geneva, 2003. 2549-2552.