A Parallel, Cognition-oriented Fundamental Frequency Estimation Algorithm

Glavitsch, Ulrike

doi:10.1016/b978-1-78548-253-3.50009-3

Cited by 1 publication

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two methods where stable intervals are computed based on pitch-scaled energy computation (PITCH-SCALED) and based on a fixed-size window length (FIXED-SIZE) are evaluated against the ideal method (baseline system) where stable intervals are calculated using pitch-synchronous window lengths. The baseline system uses a fundamental frequency estimation algorithm that has shown to achieve very low gross pitch error (GPE) rates on a clean speech database [16]. The FIXED_SIZE method uses the whole frame length of 20 ms as window length.…”

Section: Evaluation Of Methodsmentioning

confidence: 99%

“…A concrete speech processing task, namely a pitchdetection algorithm, has been implemented using this strategy [16]. It finds reliable pitch estimates on the high-energy stable intervals first and propagates them to unstable intervals in a second step.…”

Section: Role Of Stable Intervalsmentioning

confidence: 99%

“…Unstable intervals, however, may show significant energy rises or decays. Stable and unstable intervals (in general: stability intervals) have been presented as anchor points of detection in the context of a fundamental frequency (F 0 ) estimation algorithm [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Stable and unstable intervals as a basic segmentation procedure of the speech signal

Glavitsch¹,

Li²,

Dellwo³

2015

Interspeech 2015

Self Cite

View full text Add to dashboard Cite

The concept of acoustically stable and unstable intervals to structure continuous speech is introduced. We present a method to compute stable intervals efficiently and reliably as a bottom-up approach at an early processing stage. We argue that such intervals stand in close relation to the rhythm of speech as they contribute to the overall temporal organization of the speech production process and the acoustic signal (stable intervals = intervals of reduced movement of certain articulators; unstable intervals = intervals of enhanced movement of certain articulators). To test the relationship of stability intervals with speech rhythm we investigated the between-speaker variability of stable and unstable intervals in the TEVOID corpus. Results revealed that significant between-speaker variability exists. We hypothesize from our findings that the basic segmentation of speech into stable and unstable intervals is a process that might play a role in human perception and processing of speech.

show abstract

Section: Evaluation Of Methodsmentioning

confidence: 99%

Section: Role Of Stable Intervalsmentioning

confidence: 99%