Computer Assisted Transcription: General Framework
This chapter described the common basics on which are grounded the computer assisted transcription approaches described in the three subsequent chapters: Chaps. 3, 4 and 5. Besides, a general overview is provided of the common features characterizing the up-to-date systems we have employed for handwritten text and speech recognition.
Specific mathematical formulation and modeling adequate for interactive transcription of handwritten text images and speech signals are derived from a particular instantiation of the interactive–predictive general framework already introduced in Sect. 1.3.3. Moreover, on this ground and by adopting the passive left-to-right interaction protocol described in Sect. 1.4.2, the two basic computer assisted handwriting and speech transcription approaches were developed (detailed in Chaps. 3 and 4, respectively), along with the evaluation measures used to assess their performance.
KeywordsLanguage Model Speech Signal Automatic Speech Recognition Viterbi Algorithm Word Sequence
- 2.Jelinek, F. (1998). Statistical methods for speech recognition. Cambridge: MIT Press. Google Scholar
- 4.Kneser, R., & Ney, H. (1995). Improved backing-off for n-gram language modeling. In Proceedings of the international conference on acoustics, speech and signal processing (ICASSP) (Vol. 1, pp. 181–184). Google Scholar
- 5.Liu, P., & Soong, F. K. (2006). Word graph based speech recognition error correction by handwriting input. In Proceedings of the international conference on multimodal interfaces (ICMI’06) (pp. 339–346), New York, NY, USA. New York: ACM. Google Scholar
- 6.Serrano, N., Sanchis, A., & Juan, A. (2010). Balancing error and supervision effort in interactive–predictive handwritten text recognition. In Proceedings of the international conference on intelligent user interfaces (IUI’10) (pp. 373–376), Hong Kong, China. Google Scholar