Prosodic Focus

Abstract

This chapter provides an introduction to the phenomenon of prosodic focus, as well as to the theory of Alternative Semantics. Alternative Semantics provides an insightful account of what prosodic focus means, and gives us a notation that can help with better characterizing focus‐related phenomena and the terminology used to describe them. We can also “translate” theoretical ideas about focus and givenness into this notation to facilitate a comparison between frameworks. The discussion will partly be structured by an evaluation of the theories of givenness, the theory of relative givenness, and Unalternative Semantics, but we will cover a range of other ideas and proposals in the process. The chapter concludes with a discussion of phonological issues, and of association with focus.

Focus and Intensification in the Semantics of Brow Raise

“…Following Wagner (2020), a reviewer states the following objection. 5 There are multiple ways to reduce noise, but in English they are insufficient to mark focus unless they are accompanied by a shift in prominence.…”

“…And if so, are they a challenge to Alternative Semantics? The controversy only deepened when Wagner (2020) noted that in spoken language the unity of focus and intensification is at best partial: focus doesn't just require accenting the focused element but also deaccenting the unfocused (given) parts, whereas no such requirement holds for intensification. This might suggest that in the end the apparent connection between (1) and ( 2) is accidental.…”

Controllable Emphasis with zero data for text-to-speech

“…Salient constituents in utterances, typically expressing new information, are intonationally focalized, bringing them to the informational fore. While the interaction between information structure and its acoustic correlates is nuanced and complex (see [1] for an overview), we follow [2] and much related work in characterizing narrow focus as affecting a single word/constituent, as opposed to broad/wide focus affecting the entire event denoted by the sentence. Consider the following examples from [2]:…”

“…(1e) is uttered with wide focus when it answers (1d), an outof-the-blue context, and with a narrow focus when uttered as an answer to (1a-c): specifically subject focus in (1a), verb focus in (1b), object focus in (1c). The objective of this paper is to understand how we can provide "narrow focus" word-level emphasis controllability for multiple voices and languages (1) without quality degradation, (2) without annotation, (3) without recordings and (4) if possible without model re-training. While context awareness of TTS system has vastly improved (see [3], [4] among others), automated output does not always assign the correct intonation to cases like (1e), given preceding context .…”

“…We build one such model as our upper anchor, as detailed in section 2. 1 While this technique works well for the speaker for which 'emphasis recordings' are available, it does not directly scale to new speakers or different languages. An alternative technique adopted with varying degrees of success consists in annotating existing expressive recordings for emphasis [9,10,11]; while this makes recordings not needed, scaling to new voices/languages is still expensive and time consuming, given the need for extensive annotation.…”