Feasibility of Single Channel Speaker Separation Based on Modulation Frequency Analysis

Schimmel, Steven M.; Atlas, Les; Nie, Kaibao

doi:10.1109/icassp.2007.366985

Cited by 33 publications

(23 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have shown the importance of joint acoustic and modulation frequency concept in signal analysis and synthesis, as well as single-channel talker separation and coding 13 applications ( [2,30,33]). We presented a dimensionality reduction method for modulation spectral features which could be tailored to various classification tasks.…”

Section: Discussionmentioning

confidence: 99%

Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features

Markaki

Stylianou

2011

Speech Communication

View full text Add to dashboard Cite

In audio content analysis, the discrimination of speech and non-speech is the first processing step before speaker segmentation and recognition, or speech transcription. Speech/non-speech segmentation algorithms usually consist of a frame based scoring phase using MFCC features, combined with a smoothing phase. In this paper, a content based speech discrimination algorithm is designed to exploit long-term information inherent in modulation spectrum. In order to address the varying degrees of redundancy and discriminative power of the acoustic and modulation frequency subspaces, we first employ a generalization of SVD to tensors (Higher Order SVD) to reduce dimensions. Projection of modulation spectral features on the principal axes with the higher energy in each subspace results in a compact set of features with minimum redundancy. We further estimate the relevance of these projections to speech discrimination based on mutual information to the target class. This system is built upon a segment based SVM classifier in order to recognize the presence of voice activity in audio signal. Detection experiments using Greek and U.S. English broadcast news data composed of many speakers in various acoustic conditions suggest that the system provides complementary information to state-of-the-art melcepstral features.

show abstract

Section: Discussionmentioning

confidence: 99%

Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features

Markaki

Stylianou

2011

Speech Communication

View full text Add to dashboard Cite

show abstract

“…[21][22][23] Modulation filtering aims at retaining slow varying envelopes of spectral bands coming from nonstationary signals without affecting the signal's phase and fine-structure. This feature set assigns high frequency values to the spectrum parts affecting the cochlea of the listener while emphasizing the temporal modulation.…”

Section: A Temporal Modulation Featuresmentioning

confidence: 99%

A transfer learning framework for predicting the emotional content of generalized sound events

Ntalampiras

2017

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Predicting the emotions evoked by generalized sound events is a relatively recent research domain which still needs attention. In this work a framework aiming to reveal potential similarities existing during the perception of emotions evoked by sound events and songs is presented. To this end the following are proposed: (a) the usage of temporal modulation features, (b) a transfer learning module based on an echo state network, and (c) a k-medoids clustering algorithm predicting valence and arousal measurements associated with generalized sound events. The effectiveness of the proposed solution is demonstrated after a thoroughly designed experimental phase employing both sound and music data. The results demonstrate the importance of transfer learning in the specific field and encourage further research on approaches which manage the problem in a synergistic way.

show abstract

“…If modulation frequency can be consistently extracted, it provides a potential third orthogonal dimension along which signal components can be separated and clustered. The target speech signal can potentially be reconstructed by selecting those localized time-frequency regions that exhibit a particular common modulation frequency [11]. Nevertheless, accurate estimation of modulation frequency can be quite difficult for natural signals.…”

Section: I-b Uses Of Mdulation Frequencymentioning

confidence: 99%

“…Unfortunately, an analysis frame that is long enough to retain an entire modulation period will inevitably average out frequency fluctuations of shorter duration. Rather than attempting to estimate modulation frequency itself (as in [11]), we attempt to estimate correlations in the short-time frequency modulation over distinct frequency channels, with the goal of identifying frequency bins that are highly correlated with one another in terms of instantaneous frequency. This method requires the estimation of neither multi-pitch trajectories nor the modulation frequency itself.…”

Section: Signal Separation Based On Modulation Frequencymentioning

confidence: 99%

Single-channel speech separation based on modulation frequency

Lingyun

Stern

2008

2008 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This paper describes an algorithm that performs a simple form of computational auditory scene analysis to separate multiple speech signals from one another on the basis of the modulation frequencies of the components. The most novel aspect of the algorithm is the use of the cross-correlation of the instantaneous frequencies of the components of a signal to identify and separate those components that are likely have been produced by a common sound source. The putative desired target speech signal is reconstructed by choosing those components that have the greatest mutual correlation, and then using extrinsic information such as fundamental frequency or speaker identification to determine which component clusters belong to which speaker. The system was evaluated by comparing speech recognition accuracy of a target speech signal that was extracted from a mixture of two speakers. It was found that recognition accuracy obtained when the separation was based on cross-correlation of changes in instantaneous frequency was better than the accuracy obtained when the separation was performed on the basis of fundamental frequency alone, for both the DARPA Resource Management Database and the Grid database used in the 2006 Speech Separation Challenge.

show abstract

Feasibility of Single Channel Speaker Separation Based on Modulation Frequency Analysis

Cited by 33 publications

References 15 publications

Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features

Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features

A transfer learning framework for predicting the emotional content of generalized sound events

Single-channel speech separation based on modulation frequency

Contact Info

Product

Resources

About