Speech/non-speech segmentation based on phoneme recognition features

DOI10.1155/ASP/2006/90495MaRDI QIDQ2500916zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Janez Žibert, Nikola Pavešić, France Mihelič

Publication date 28 August 2006

Published in EURASIP Journal on Applied Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1155/asp/2006/90495

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Review text

Summary: This work assesses different approaches for speech and non-speech segmentation of audio data and proposes a new, high-level representation of audio signals based on phoneme recognition features suitable for speech/non-speech discrimination tasks. Unlike previous model-based approaches, where speech and non-speech classes were usually modeled by several models, we develop a representation where just one model per class is used in the segmentation process. For this purpose, four measures based on consonant-vowel pairs obtained from different phoneme speech recognizers are introduced and applied in two different segmentation-classification frameworks. The segmentation systems were evaluated on different broadcast news databases. The evaluation results indicate that the proposed phoneme recognition features are better than the standard mel-frequency cepstral coefficients and posterior probability-based features (entropy and dynamism). The proposed features proved to be more robust and less sensitive to different training and unforeseen conditions. Additional experiments with fusion models based on cepstral and the proposed phoneme recognition features produced the highest scores overall, which indicates that the most suitable method for speech/non-speech segmentation is a combination of low-level acoustic features and high-level recognition features.

Recommendations

• scientific article; zbMATH DE number 2090263
• scientific article; zbMATH DE number 1194178
• Transcription-based automatic segmentation of speech
• scientific article; zbMATH DE number 1414410
• Nonlinear and discriminant feature extraction applied to phonemes recognition
• Speaker independent phoneme classification in continuous speech

Cited in

(5)

• scientific article; zbMATH DE number 1194178 (Why is no real title available?)
• Assessing the Performance of Three Methods for Separating Non-Spontaneous and Spontaneous Speech Through Simulation
• scientific article; zbMATH DE number 2087683 (Why is no real title available?)
• Research on a word segmentation algorithm based on the Uyghur phoneme acoustic feature
• Online speech/music segmentation based on the variance mean of filter bank energy

This page was built for publication: Speech/non-speech segmentation based on phoneme recognition features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2500916)