Using hierarchical information structure for prosody prediction in content-to-speech applications

Domínguez, Mónica; Farrús, Mireia; Burga, Alicia; Wanner, Leo

doi:10.21437/speechprosody.2016-209

Cited by 7 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the prediction of expressions from text and the synthesis of a particular expression have been integrated together [14]. In addition, prosody has been structured as a multi-level hierarchy for emotional speech synthesis [5], and its correlation with both hierarchical information structure and discourse has also been analyzed for speech synthesis purposes [15,16,17]. However, the general trend is to work on sentence level.…”

Section: Related Workmentioning

confidence: 99%

Paragraph Prosodic Patterns to Enhance Text-to-Speech Naturalness

Peiró-Lilja¹,

Farrús²

2018

Speech Prosody 2018

Self Cite

View full text Add to dashboard Cite

Speech synthesis has reached a reasonable high quality in recent years. However, there is still room for improvement in terms of naturalness and expressiveness when dealing with large multisentential discourse, since most text-to-speech synthesizers do not fully take into account the prosodic differences that have been observed in discourse units such as paragraphs. This work presents an implementation of paragraph-based prosodic patterns into the open-source MARYTTS platform, enriching its prosody output by means of intra-and inter-paragraph prosodic features. The set of characteristics include pitch decay, pitch range and speech rate variation (as intra-paragraph features), as well as paragraph break pauses and speech rate variation (as inter-paragraph features), previously analyzed in a large set of TED Talks and read-speech sections of the Spoken Wikipedia Corpus. The perception tests, performed both in English and German parametric voices, suggest that paragraph-based features should be further studied and taken into account on future implementations to synthesize large discourse speech.

show abstract

Section: Related Workmentioning

confidence: 99%

Paragraph Prosodic Patterns to Enhance Text-to-Speech Naturalness

Peiró-Lilja¹,

Farrús²

2018

Speech Prosody 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…A total of five partitions are identified, including three spans at level 1 (L1), a specifier (SP1), theme (T1) and rheme (R1), and two embedded spans at level 2 (L2) 2 in the rheme, a theme (T1(R1)) and a rheme (R1(R1)). 3 ( A hierarchical thematicity structure of this kind has been shown to correlate better with ToBI labels than binary flat thematicity [9]. Such a correlation still does not solve the problem of a one-to-one mapping between a specific intonation label (e.g., H*) to a static acoustic parameter (e.g., an increase of 50% in fundamental frequency).…”

Section: Motivation and Backgroundmentioning

confidence: 99%

“…In the early 2000ies, there were some attempts to introduce some basic concepts of Information Structure in TTS applications, in particular, thematicity, understood as the partition of a sentence into theme (i.e., what the sentence in about) and rheme (i.e., what is said about the theme); see [6,7] among others. However, a binary flat representation of thematicity of this kind has been proved to be insufficient to describe long complex sentences, whereas the hierarchical tripartite approach proposed in [8] within the Meaning-Text Theory yields a better correspondence to prosodic patterns as shown in [9,10].…”

Section: Introductionmentioning

confidence: 99%

Towards expressive prosody generation in TTS for reading aloud applications

Domínguez¹,

Burga²,

Farrús³

et al. 2018

IberSPEECH 2018

Self Cite

View full text Add to dashboard Cite

Conversational interfaces involving text-to-speech (TTS) applications have improved expressiveness and overall naturalness to a reasonable extent in the last decades. Conversational features, such as speech acts, affective states and information structure have been instrumental to derive more expressive prosodic contours. However, synthetic speech is still perceived as monotonous, when a text that lacks those conversational features is read aloud in the interface, i.e. it is fed directly to the TTS application. In this paper, we propose a methodology for pre-processing raw texts before they arrive to the TTS application. The aim is to analyze syntactic and information (or communicative) structure, and then use the high-level linguistic features derived from the analysis to generate more expressive prosody in the synthesized speech. The proposed methodology encompasses a pipeline of four modules: (1) a tokenizer, (2) a syntactic parser, (3) a communicative parser, and (3) an SSML prosody tag converter. The implementation has been tested in an experimental setting for German, using web-retrieved articles.

show abstract

“…The corpus has been processed using Bohnet's [12] joint tagger and dependency parser to obtain lexical and syntactic features and annotated manually with information structure (more precisely, with Thematicity 2 features from Mel'čuk's [9] communicative structure), following the guidelines established by Bohnet et al [13]. Further details on how information structure is understood can be found in the authors' work [6] and [14] on its correlation to prosody.…”

Section: The Datasetmentioning

confidence: 99%

Combining acoustic and linguistic features in phrase-oriented prosody prediction

Domínguez¹,

Farrús²,

Wanner³

2016

Speech Prosody 2016

Self Cite

View full text Add to dashboard Cite

Intonation is traditionally considered to be the most important prosodic feature, whereupon an important research effort has been devoted to automatic segmentation and labeling of speech samples to grasp intonation cues. A number of studies also show that when duration or intensity are incorporated, automatic prosody labeling is further improved. However, the combination of word level acoustic features still attains poor results when machine learning techniques are applied on annotated corpora to derive intonation for speech synthesis applications. To address this problem, we present an experimental setup for the development of a hierarchical prosodic structure model which combines linguistic features, including information structure, and three acoustic elements (intensity, pitch and duration). We show empirically that this combination leads to a considerably more accurate representation of prosody and, consequently, a more reliable automatic labeling of speech corpora for machine learning.

show abstract

Using hierarchical information structure for prosody prediction in content-to-speech applications

Cited by 7 publications

References 17 publications

Paragraph Prosodic Patterns to Enhance Text-to-Speech Naturalness

Paragraph Prosodic Patterns to Enhance Text-to-Speech Naturalness

Towards expressive prosody generation in TTS for reading aloud applications

Combining acoustic and linguistic features in phrase-oriented prosody prediction

Contact Info

Product

Resources

About