Timing patterns in fluent and disfluent spontaneous speech

@article{OShaughnessy1995TimingPI,
  title={Timing patterns in fluent and disfluent spontaneous speech},
  author={Douglas D. O'Shaughnessy},
  journal={1995 International Conference on Acoustics, Speech, and Signal Processing},
  year={1995},
  volume={1},
  pages={600-603 vol.1}
}
  • D. O'Shaughnessy
  • Published 9 May 1995
  • Computer Science
  • 1995 International Conference on Acoustics, Speech, and Signal Processing
Most previous acoustic analysis of speech has examined data from speakers who carefully pronounce their speech, usually by reading prepared texts. Natural spontaneous or conversational speech differs from careful or read speech, especially concerning hesitation phenomena and variable speaking rates. We examine and model global speaking rate, how it varies for both fluent and disfluent spontaneous speech, in terms of the linguistic content of the utterances. Speakers tend to maintain a fixed… 
Measuring and Compensating for the Effects of Speech Rate in Large Vocabulary Continuous Speech Recognition
TLDR
The phone duration percentile, a comparison of measured versus expected phone duration, is shown to be robust with respect to lexical content and consistent with previous findings about the statistics of long-term and short-term speech rate.
Hesitations in Spoken Dialogue Systems
Proceedings of DiSS 2017, the 8th Workshop on Disfluency in Spontaneous Speech
Following the successes of the previously organized Disfluency in Spontaneous Speech (DiSS) workshops held in Berkeley (1999), Edinburgh (2001), Goteborg (2003), Aix-en-Provence (2005), Tokyo (2010
Prolongation in German
We investigate segment prolongation as a means of disfluent hesitation in spontaneous German speech. We describe phonetic and structural features of disfluent prolongation and compare it to data of
Synthesized lengthening of function words - The fuzzy boundary between fluency and disfluency
TLDR
This study tests the effects of step-wise increases of synthesized lengthening on user ratings and interaction speed and assumes that these characteristics of lengthening make it a key component in spoken dialogue systems that are capable of producing disfluencies.
Are we all disfluent in our own special way and should dialogue systems also be
TLDR
This study explores interand intra-speaker variation in use of timemanagement strategies, aiming to describe in detail speaker-specific productions of selected time-buying disfluencies for later use in synthesis.
D ISFLUENT L ENGTHENING IN S PONTANEOUS S PEECH
We investigate lengthening in spontaneous speech with the aim in mind to use it as a time-management strategy in incremental spoken dialogue systems. lengthening is a common feature of speech,
Deriving a strategy for synthesizing lengthening disfluencies based on spontaneous conversational speech data
TLDR
This paper analyzed disfluency-related lengthening in the ”monomodal” half of the GECO corpus and postulate a disfluencies insertion strategy for synthetic speech that prioritizes lengthening phenomena based on the results obtained in this study.
On the Significance of Speech Pauses in Depressive Disorders: Results on Read and Spontaneous Narratives
TLDR
The results suggest that depressive disorders affect speech quality and speech production through pause and clause durations, as well as, clause quantities, suggest a strong general effect of depressive symptoms on cognitive and psychomotor functions.
Pre-Course Key Segment Analysis of Online Lecture Videos
TLDR
Both the general trend and the high accuracy of selected key segments prove the effectiveness of the proposed method to evaluate the importance of lecture video segments in online courses.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 18 REFERENCES
A corpus-based study of repair cues in spontaneous speech.
The occurrence of disfluencies in fully natural speech poses difficult challenges for spoken language understanding systems. For example, although self-repairs occur in about 10% of spontaneous
Correcting complex false starts in spontaneous speech
  • D. O'Shaughnessy
  • Computer Science
    Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing
  • 1994
TLDR
Identifying the nature and extent of the restart in such cases could improve the performance of an automatic speech recognizer, by allowing the elimination from consideration of some hypotheses based on spectral analysis.
Timing in text-to-speech systems
Automatic Detection and Correction of Repairs in Human-Computer Dialog
TLDR
Criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction are presented.
Integrating Multiple Knowledge Sources for Detection and Correction of Repairs in Human-Computer Dialog
TLDR
The authors present criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction, and preliminary results show that pattern matching is effective at detecting repairs without excessive overgeneration.
Segment durations in a syllable frame
TLDR
It was found that whereas segments in pre-pausal sentence-final syllables undergo greater lengthening in the rhyme than in the onset, segments in sentence-internal syllables are lengthened or compressed more uniformly across the syllable.
Articulation rate and the duration of syllables and stress groups in connected speech.
  • T. Crystal, A. House
  • Mathematics, Medicine
    The Journal of the Acoustical Society of America
  • 1990
TLDR
It was found that variability of articulation rate, measured as the average syllable duration for interpause intervals (runs), is not random, but is the natural consequence of the content of the run.
Effects of speaking rate on the behavior of tense and lax vowel durations
The current study investigated the effects of speaking rate on the acoustic durations of four pairs of American English tense and lax vowels [i– i , ae–e, ɑ–ʌ, u– u ] in four different postvocalic
Effects of noise on speech production: acoustic and perceptual analyses.
TLDR
The nature of the acoustic changes that taken place when speakers produce speech under adverse conditions such as noise, psychological stress, or high cognitive load are discussed and the role of training and feedback in controlling and modifying a talker's speech to improve performance of current speech recognizers is discussed.
Characterization and modeling of speech-segment durations
  • T. Crystal, A. House
  • Computer Science
    ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1986
Two types of analyses have been performed on the measured durations of recordings produced by six talkers reading two scripts of approximately 300 words each. The texts, the combined visual-auditory
...
1
2
...