Parse scoring with prosodic information: an analysis/synthesis approach

Ostendorf, Mari; Wightman, Colin W.; Veilleux, Nanette

doi:10.1006/csla.1993.1010

Cited by 38 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LMs alone are already very good; we have, however, to consider that they cannot be (Kompe, 1997). Similar classi®cation experiments with syntactic±prosodic boundaries are reported in (Wang and Hirschberg, 1992;Ostendorf et al, 1993), where HMMs or classi®cation trees were used. The authors rely on perceptual±prosodic labels created on the basis of the ToBI system (Beckman and Ayers, 1994); for such labels, however, a much smaller amount of data can be obtained than in our case, cf.…”

Section: Automatic Classi®cation Of Boundariesmentioning

confidence: 97%

“…Our recognition rates are higher maybe because of the larger amount of training data; note, however, that the studies cannot be compared in a strict sense because they dier considerably w.r.t. several factors: the labelling systems are dierent, the numbers of classes dier, Wang and Hirschberg (1992) included the end of turns as label, Ostendorf et al (1993) used elicited, systematically ambiguous material that already because of that should be marked prosodically to a greater extent, and the languages dier.…”

Section: Automatic Classi®cation Of Boundariesmentioning

confidence: 99%

See 1 more Smart Citation

M = Syntax + Prosody: A syntactic–prosodic labelling scheme for large spontaneous speech databases

Batliner

Kompe

Kießling

et al. 1998

Speech Communication

View full text Add to dashboard Cite

In automatic speech understanding, division of continuous running speech into syntactic chunks is a great problem. Syntactic boundaries are often marked by prosodic means. For the training of statistical models for prosodic boundaries large databases are necessary. For the German Verbmobil (VM) project (automatic speech-to-speech translation), we developed a syntactic±prosodic labelling scheme where dierent types of syntactic boundaries are labelled for a large spontaneous speech corpus. This labelling scheme is presented and compared with other labelling schemes for perceptual±prosodic, syntactic, and dialogue act boundaries. Interlabeller consistencies and estimation of eort needed are discussed. We compare the results of classi®ers (multi-layer perceptrons (MLPs) and n-gram language models) trained on these syntactic±prosodic boundary labels with classi®ers trained on perceptual±prosodic and pure syntactic labels. The main advantage of the rough syntactic±prosodic labels presented in this paper is that large amounts of data can be labelled with relatively little eort. The classi®ers trained with these labels turned out to be superior with respect to purely prosodic or syntactic labelling schemes, yielding recognition rates of up to 96% for the two-class-problem`boundary versus no boundary'. The use of boundary information leads to a marked improvement in the syntactic processing of the VM system. Ó 1998 Elsevier Science B.V. All rights reserved. ZusammenfassungDie Segmentierung von kontinuierlich gesprochener Sprache in syntaktisch sinnvolle Einheiten ist f ur die automatische Sprachverarbeitung ein groûes Problem. Syntaktische Grenzen sind oft prosodisch markiert. Um prosodische Grenzen mit statistischen Modellen bestimmen zu k onnen, ben otigt man allerdings groûe Trainingskorpora. F ur das Forschungsprojekt Verbmobil zur automatischen Ubersetzung spontaner Sprache wurde daher ein syntaktisch±pro-sodisches Annotationsschema entwickelt und auf ein groûes Korpus angewendet. Dieses Schema wird mit anderen Annotationsschemata verglichen, mit denen prosodisch±perzeptive, rein syntaktische bzw. Dialogakt-Grenzen etikettiert wurden; Konsistenz der Annotation und ben otigter Aufwand werden diskutiert. Das Ergebnis einer automatischen Klassi®kation (multi-layer perceptrons bzw. Sprachmodelle) f ur diese neuen Grenzen wird mit den Erkennungsraten verglichen, die f ur die anderen Grenzen erzielt wurden. Der Hauptvorteil der groben syntaktisch± prosodischen Grenzen, die in diesem Aufsatz eingef uhrt werden, besteht darin, daû ein groûes Trainingskorpus in Speech Communication 25 (1998) 193±222 * Corresponding author. E-mail: batliner@informatik.uni-erlangen.de. 0167-6393/98/$ ± see front matter Ó 1998 Elsevier Science B.V. All rights reserved. PII: S 0 1 6 7 -6 3 9 3 ( 9 8 ) 0 0 0 3 7 -5 relativ kurzer Zeit erstellt werden kann. Die Klassi®katoren, die mit diesem Korpus trainiert wurden, erzielten bessere Ergebnisse als alle fr uher verwendeten; die beste Erkennungsrate lag bei 96% f ur das Zwei-Klassen-Problem...

show abstract

Section: Automatic Classi®cation Of Boundariesmentioning

confidence: 97%

Section: Automatic Classi®cation Of Boundariesmentioning

confidence: 99%

M = Syntax + Prosody: A syntactic–prosodic labelling scheme for large spontaneous speech databases

Batliner

Kompe

Kießling

et al. 1998

Speech Communication

View full text Add to dashboard Cite

show abstract

“…Recently more progress has been claimed in the relation between ASR performance and prosodic properties of utterances (e.g. Hirschberg et al, 2000;Litman et al, 2000;Hirschberg, 1999;Ostendorf et al, 1993;Shriberg et al, 1998). N€ o oth et al (1999) show that the integration of prosodic information might greatly improve the processing speed of the word search.…”

Section: Prosodic Features and Asrmentioning

confidence: 99%

Emotions, speech and the ASR framework

Bosch

2003

Speech Communication

View full text Add to dashboard Cite

Automatic recognition and understanding of speech are crucial steps towards natural human-machine interaction. Apart from the recognition of the word sequence, the recognition of properties such as prosody, emotion tags or stress tags may be of particular importance in this communication process. This paper discusses the possibilities to recognize emotion from the speech signal, primarily from the viewpoint of automatic speech recognition (ASR). The general focus is on the extraction of acoustic features from the speech signal that can be used for the detection of the emotional state or stress state of the speaker.After the introduction, a short overview of the ASR framework is presented. Next, we discuss the relation between recognition of emotion and ASR, and the different approaches found in the literature that deal with the correspondence between emotions and acoustic features. The conclusion is that automatic emotional tagging of the speech signal is difficult to perform with high accuracy, but prosodic information is nevertheless potentially useful to improve the dialogue handling in ASR tasks on a limited domain.

show abstract

“…In [7] prosodic information was used to score alternative parses of the same word sequence. Our approach di ers from that one, because we use the prosodic information in a preprocessing step where alternative string hypotheses are selected based on prosodic information and are parsed afterwards.…”

Section: Resultsmentioning

confidence: 99%

Prosody, empty categories and parsing-a success story

Batliner¹,

Feldhaus²,

Geissler³

et al.

Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

View full text Add to dashboard Cite

We describe a number of experiments that demonstrate the usefulness of prosodic information for a processing module which parses spoken utterances with a feature-based grammar employing empty categories. We show that by requiring certain prosodic properties from those positions in the input, where the presence of an empty category has to be hypothesized, a derivation can be accomplished more e ciently. The approach has been implemented in the machine translation project Verbmobil and results in a signi cant reduction of the work-load for the parser.

show abstract

Parse scoring with prosodic information: an analysis/synthesis approach

Cited by 38 publications

References 0 publications

M = Syntax + Prosody: A syntactic–prosodic labelling scheme for large spontaneous speech databases

M = Syntax + Prosody: A syntactic–prosodic labelling scheme for large spontaneous speech databases

Emotions, speech and the ASR framework

Prosody, empty categories and parsing-a success story

Contact Info

Product

Resources

About