1 |
DeepFry: Identifying Vocal Fry Using Deep Neural Networks ...
|
|
|
|
Abstract:
Vocal fry or creaky voice refers to a voice quality characterized by irregular glottal opening and low pitch. It occurs in diverse languages and is prevalent in American English, where it is used not only to mark phrase finality, but also sociolinguistic factors and affect. Due to its irregular periodicity, creaky voice challenges automatic speech processing and recognition systems, particularly for languages where creak is frequently used. This paper proposes a deep learning model to detect creaky voice in fluent speech. The model is composed of an encoder and a classifier trained together. The encoder takes the raw waveform and learns a representation using a convolutional neural network. The classifier is implemented as a multi-headed fully-connected network trained to detect creaky voice, voicing, and pitch, where the last two are used to refine creak prediction. The model is trained and tested on speech of American English speakers, annotated for creak by trained phoneticians. We evaluated the ... : under submission to Interspeech 2022 ...
|
|
Keyword:
Audio and Speech Processing eess.AS; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG; Sound cs.SD
|
|
URL: https://dx.doi.org/10.48550/arxiv.2203.17019 https://arxiv.org/abs/2203.17019
|
|
BASE
|
|
Hide details
|
|
2 |
Positional biases in predictive processing of intonation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Individual Differences in the Production and Perception of Prosodic Boundaries in American English
|
|
|
|
BASE
|
|
Show details
|
|
5 |
The Interaction of Phonology and Morphology in Seri
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
6 |
A Government-Binding Parser
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Paradoxical Strength Conditions in Harmony Systems
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
8 |
Data for: Sound, structure and meaning: The bases of prominence ratings in English, French and Spanish ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Data for: Sound, structure and meaning: The bases of prominence ratings in English, French and Spanish ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
The phonological and phonetic encoding of information status in American English nuclear accents
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Nuclear vs. prenuclear accents and the encoding of information status. Poster Presentation
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Information structure, affect, and prenuclear prominence in American English
|
|
|
|
BASE
|
|
Show details
|
|
14 |
The mediating effect of information status on acoustic cues to prominence. Oral presentation
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Probabilistic relationship between pitch accents and information status in public speech
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Acoustic cues for the perception of the information status of words in speech
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Individual differences and patterns of convergence in prosody perception
|
|
|
|
In: Laboratory Phonology: Journal of the Association for Laboratory Phonology; Vol 8, No 1 (2017); 22 ; 1868-6354 (2017)
|
|
BASE
|
|
Show details
|
|
19 |
Accounting for context and variability in a prominence-based model of discourse meaning. Oral presentation
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Contrast preservation and constraints on individual phonetic variation
|
|
|
|
BASE
|
|
Show details
|
|
|
|