Voice signatures
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Most current spoken-dialog systems only extract sequences of words from a speaker's voice. This largely ignores other useful information that can be inferred from speech such as gender, age, dialect, or emotion. These characteristics of a speaker's voice, voice signatures, whether static or dynamic, can be useful for speech mining applications or for the design of a natural spoken-dialog system. This paper explores the problem of extracting automatically and accurately voice signatures from a speaker's voice. We investigate two approaches for extracting speaker traits: the first focuses on general acoustic and prosodic features, the second on the choice of words used by the speaker. In the first approach, we show that standard speech/nonspeech HMM, conditioned on speaker traits and evaluated on cepstral and pitch features, achieve accuracies well above chance for all examined traits. The second approach, using support vector machines with rational kernels applied to speech recognition lattices, attains an accuracy of about 8.1 % in the task of binary classification of emotion. Our results are based on a corpus of speech data collected from a deployed customer-care application (HMIHY 0300). While still preliminary, our results are significant and show that voice signatures are of practical interest in real-world applications.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(2002) · doi:10.1109/icme.2002.1035887 · Cited by 69 · cited 1×
“[11, 12, 13, 14] extracted a set of utterance-level statistics on acoustics such as pitch and energy.”
Background
Cited by
Baker, R. S. J. D., D'Mello, S. K., Rodrigo, M. M. T., & Graesser, A. C. (2010) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2009.12.003 · Cited by 936
SoundSense: scalable sound sensing for people-centric applications on mobile phones
Lu, H., Pan, W., Lane, N. D., Choudhury, T., & Campbell, A. T. (2009) · Proceedings of the 7th international conference on Mobile systems, applications, and services · doi:10.1145/1555816.1555834 · Cited by 581
Challenges in real-life emotion annotation and machine learning based detection
Devillers, L., Vidrascu, L., & Lamel, L. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.03.007 · Cited by 342
Automatic detection of learner’s affect from conversational cues
D’Mello, S. K., Craig, S. D., Witherspoon, A., McDaniel, B., & Graesser, A. (2008) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-007-9037-6 · Cited by 317
Paralinguistics in speech and language—State-of-the-art and the challenge
Schuller, B., Steidl, S., Batliner, A., Burkhardt, F., Devillers, L., Müller, C., & Narayanan, S. (2013) · Computer Speech & Language · doi:10.1016/j.csl.2012.02.005 · Cited by 284
Schlattmann, P. (2009) · Statistics for Biology and Health · doi:10.1007/978-3-540-68651-4_4 · Cited by 283
Emotion Recognition based on Phoneme Classes
Lee, C. M., Yildirim, S., Bulut, M., Kazemzadeh, A., Busso, C., Deng, Z., Lee, S., & Narayanan, S. (2004) · Interspeech 2004 · doi:10.21437/interspeech.2004-322 · Cited by 228
“A recent study has also included emotion as an indicator/signature of a speaker in the context of speech-based content mining applications [3].”
BackgroundClass-level spectral features for emotion recognition
Bitouk, D., Verma, R., & Nenkova, A. (2010) · Speech Communication · doi:10.1016/j.specom.2010.02.010 · Cited by 219
“…2005; Hasegawa-Johnson et al., 2004; Vlasenko et al., 2007; Grimm et al., 2006; Schuller and Rigoll, 2006; Meng et al., 2007; Sato and Obuchi, 2007; Kim et al., 2007; Hu et al., 2007; Shafran et al., 2003; Shamia and Kamel, 2005; Vlasenko et al., 2008; Vondra and Vich, 2009; Wang and Guan, 2005).”
Fear-type emotion recognition for future audio-based surveillance systems
Clavel, C., Vasilescu, I., Devillers, L., Richard, G., & Ehrette, T. (2008) · Speech Communication · doi:10.1016/j.specom.2008.03.012 · Cited by 180
“Low-level features such as spectral and cepstral features, were initially used for speech processing systems, but can also be used for emotion classification systems (Shafran et al., 2003; Kwon et al., 2003).”
MethodInfluence of contextual information in emotion annotation for spoken dialogue systems
Callejas, Z., & López-Cózar, R. (2008) · Speech Communication · doi:10.1016/j.specom.2008.01.001 · Cited by 86
“.32 to 0.42 in (Shafran et al., 2003) and below 0.48 in (Ang et al., 2002; Lee and Narayanan (2005) ), there is not a deep discussion about the problematic of Kappa values in the area, not even in papers explicitly devoted to challenges in emotion annotation (e.g. Devillers et al., 2005 ).”
BackgroundInfluential
Metadata
- Authors
- Shafran, I., Riley, M., & Mohri, M.
- Venue
- 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721)
- Publisher
- IEEE
- Published
- 2004-09-07
- Pages
- 31-36
- OpenAlex
- W2293299267
- Cited by
- 111
- References
- 1
- FWCI
- 6.94
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.