Answers are grounded in this paper and cite their sources.
Following the rapid proliferation of mobile devices, especially smartphones, both server-based and embedded speech and multimodal applications started to emerge. These range from simpler applications where speech recognition is followed by a known task such as voice search or messaging, to more complex systems such as speech-to-speech translation, educational applications, or personal assistants.
No takes yet. Share an insight, caveat, or question.
Hakkani‐Tür et al. (2011) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: