Parsers, prominence, and pauses
نویسندگان
چکیده
We present results of a comparison between two prosody prediction algorithms, showing that the incorporation of information from a parser results in signi cantly improved performance for our text-tospeech synthesiser. We used a stochastic tree-based parser to generate a tagged and bracketed representation of the input text, and then interpreted this higher-level information to produce a ToBI-type prosodic annotation of the text. From this annotation an intonation contour was predicted for use in synthesising the speech. Results show that prediction of prosodic phrasing and focal prominence are improved by 56% and 62% respectively over previous methods compared against a human reading of the same test utterances.
منابع مشابه
Chunks and Dependencies: Bringing Processing Evidence to Bear on Syntax
At least some psycholinguists exploring how sentences are structured in linguistic behavior have concluded that the “performance structures” that emerge from experimental data differ from the syntactic structures hypothesized by linguists. For example, one measure of structure is the location and relative prominence of pauses when subjects read sentences aloud. Experiments have indicated that t...
متن کاملPerception of prosodic prominence and boundaries by L1 and L2 speakers of English
This study provides a direct comparison of boundary and prominence perception strategies between Japanese EFL learners and native speakers of English using the Rapid Prosody Transcription (RPT) method. Although RPT experiments are available for both native English speakers [1], [2], [3] and Japanese EFL learners [4], a direct comparison of the available data is problematic as the stimuli sets u...
متن کاملHierarchical tag-graph search for spontaneous speech understanding in spoken dialog systems
It has been relatively difficult to develop natural language parsers for spoken dialog systems, not only because of the possible recognition errors, pauses, hesitations, out-ofvocabulary words, and the grammatically incorrect sentence structures, but because of the great efforts required to develop a general enough grammar with satisfactory coverage and flexibility to handle different applicati...
متن کاملTowards Learning Semantics of Spontaneous Dialog Utterances in a Hybrid Framework
In contrast to text processing, spontaneous language contains many discontinuities caused by unusual order, false starts, repairs, repetitions, pauses, etc. Data-driven connectionist learning methods and their inherent fault tolerance can consider this form of \sequential noise". We describe a new hybrid approach for a at semantic interpretation of sentences in spontaneous dialogs using symboli...
متن کاملRelative Importance in English and Persian: Thematization or Tonic Prominence?
There are two common ways to assign relative importance in spoken language: tonic prominence and thematization. The former is expressing the main points of information units in speech (Halliday, 1994), and the latter is putting an element at the beginning of a clause. This study explores how relative importance is realized in English and Persian. It also investigates how advanced Persian learne...
متن کامل