Ch5-Automatic Speech Recognition

Ch5-Automatic Speech Recognition - Search and Decoding in...

Info iconThis preview shows pages 1–7. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Search and Decoding in Speech Recognition Automatic Speech Recognition 2/13/12 Veton Kpuska 2 Automatic Speech Recognition u Spoken language understanding is a difficult task, and it is remarkable that humans do well at it. u The goal of automatic speech recognition ASR ( ASR ) research is to address this problem computationally by building systems that map from an acoustic signal to a string of words. u Automatic speech understanding ( ASU ) extends this goal to producing some sort of understanding of the sentence, rather than just the words. 2/13/12 Veton Kpuska 3 Application Areas u The general problem of automatic transcription of speech by any speaker in any environment is still far from solved. But recent years have seen ASR technology mature to the point where it is viable in certain limited domains. u One major application area is in human-computer interaction . n While many tasks are better solved with visual or pointing interfaces, speech has the potential to be a better interface than the keyboard for tasks where full natural language communication is useful, or for which keyboards are not appropriate. n This includes hands-busy or eyes-busy applications, such as where the user has objects to manipulate or equipment to control. 2/13/12 Veton Kpuska 4 Application Areas u Another important application area is telephony , where speech recognition is already used for example n in spoken dialogue systems for entering digits, recognizing yes to accept collect calls, n finding out airplane or train information, and n call-routing (Accounting, please, Prof. Regier, please). u In some applications, a multimodal interface combining speech and pointing can be more efficient than a graphical user interface without speech (Cohen et al., 1998). 2/13/12 Veton Kpuska 5 Application Areas u Finally, ASR is applied to dictation , that is, transcription of extended monologue by a single specific speaker. Dictation is common in fields such as law and is also important as part of augmentative communication (interaction between computers and humans with some disability resulting in the inability to type, or the inability to speak). The blind Milton famously dictated Paradise Lost to his daughters, and Henry James dictated his later novels after a repetitive stress injury. 2/13/12 Veton Kpuska 6 Parameters that define Speech Recognition Applications 1. One dimension of variation in speech recognition tasks is the vocabulary size . n Speech recognition is easier if the number of distinct words we need to recognize is smaller. So tasks with a two word we need to recognize is smaller....
View Full Document

Page1 / 175

Ch5-Automatic Speech Recognition - Search and Decoding in...

This preview shows document pages 1 - 7. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online