The Prosody Module

Zeißler, Viktor; Adelhardt, Johann; Batliner, Anton; Frank, Carmen; Nöth, Elmar; Shi, Rui Ping; Niemann, Heinrich

doi:10.1007/978-3-662-04230-4_8

Cited by 63 publications

(65 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each reference point, 95 features are extracted over intervals which contain a word, a word-pause-word interval or the pause between two words. A full description of the features used is beyond the scope of this paper; details and further references are given in [12]. The feature set was also used successfully for other voice and speech pathologies [7,8].…”

Section: Prosodic Featuresmentioning

confidence: 99%

Objective vs. Subjective Evaluation of Speakers with and without Complete Dentures

Haderlein

Maier

Nöth

et al. 2009

Text, Speech and Dialogue

Self Cite

View full text Add to dashboard Cite

Abstract. For dento-oral rehabilitation of edentulous (toothless) patients, speech intelligibility is an important criterion. 28 persons read a standardized text once with and once without wearing complete dentures. Six experienced raters evaluated the intelligibility subjectively on a 5-point scale and the voice on the 4-point Roughness-Breathiness-Hoarseness (RBH) scales. Objective evaluation was performed by Support Vector Regression (SVR) on the word accuracy (WA) and word recognition rate (WR) of a speech recognition system, and a set of 95 word-based prosodic features. The word accuracy combined with selected prosodic features showed a correlation of up to r = 0.65 to the subjective ratings for patients with dentures and r = 0.72 for patients without dentures. For the RBH scales, however, the average correlation of the feature subsets to the subjective ratings for both types of recordings was r < 0.4.

show abstract

Section: Prosodic Featuresmentioning

confidence: 99%

Objective vs. Subjective Evaluation of Speakers with and without Complete Dentures

Haderlein

Maier

Nöth

et al. 2009

Text, Speech and Dialogue

Self Cite

View full text Add to dashboard Cite

show abstract

“…The prosody module used in these experiments was originally developed within the VERBMOBIL project [18], mainly to speed up the linguistic analysis [19,20]. It assigns a vector of prosodic features to each word in a word hypothesis graph which is then used to classify a word w.r.t., e.g.…”

Section: Prosodic Featuresmentioning

confidence: 99%

Towards the Automatic Classification of Reading Disorders in Continuous Text Passages

Maier

Hönig

Horndasch

et al. 2009

Text, Speech and Dialogue

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper, we present an automatic classification approach to identify reading disorders in children. This identification is based on a standardized test. In the original setup the test is performed by a human supervisor who measures the reading duration and notes down all reading errors of the child at the same time. In this manner we recorded tests of 38 children who were suspected to have reading disorders. The data was confronted to an automatic system which employs speech recognition and prosodic analysis to identify the reading errors. In a subsequent classification experiment -based on the speech recognizer's output, the duration of the test, and prosodic features -94.7 % of the children could be classified correctly.

show abstract

“…However, only in the last few years has prosody really begun to find its way into ASU, most of the time within offline, i.e., in vitro, research. The only existing end-to-end system that really uses prosody is, to our knowledge, the Verbmobil system [1]. This state of affairs might be traced back to the general difficulty of carrying over theoretical work into practice as well as to the well-known differences between the two cultures: on the one hand, humanities, on the other hand, engineering.…”

Section: Automatic Speech Understandingmentioning

confidence: 99%

“…To our knowledge, no approach exists that actually uses such phonological units for the recognition of prosodic events. Of course, there are many studies that describe offline classifications of such phonological prosodic concepts; this has to be distinguished from the successful integration in an existing end-to-end-system, as we have shown within the Verbmobil project [1,5].…”

Section: The Reasons Why (Occams Razor Still Matters)mentioning

confidence: 99%

Prosodic Models, Automatic Speech Understanding, and Speech Synthesis: Towards the Common Ground?

Batliner

Möbius

2005

Text, Speech and Language Technology

Self Cite

View full text Add to dashboard Cite

Automatic speech understanding and speech synthesis, two of the major speech processing applications, impose strikingly different constraints and requirements on prosodic models. The prevalent models of prosody and intonation fail to offer a unified solution to these conflicting constraints. As a consequence, prosodic models have been applied only occasionally in end-toend automatic speech understanding systems; in contrast, they have been applied extensively in speech synthesis systems. In this paper we want to discuss the reasons for this state of affairs as well as possible strategies to overcome the shortcomings of the use of prosodic modelling in automatic speech processing.

show abstract

The Prosody Module

Cited by 63 publications

References 12 publications

Objective vs. Subjective Evaluation of Speakers with and without Complete Dentures

Objective vs. Subjective Evaluation of Speakers with and without Complete Dentures

Towards the Automatic Classification of Reading Disorders in Continuous Text Passages

Prosodic Models, Automatic Speech Understanding, and Speech Synthesis: Towards the Common Ground?

Contact Info

Product

Resources

About