1 / 18

Separation of Multispeaker Speech Using Excitation Information

Separation of Multispeaker Speech Using Excitation Information. B.Yegnanarayana, R.Kumara Swamy and S.R.Mahadeva Prasanna Dept of Computer Science and Engineering Indian Institute of Technology Madras Chennai-600036, India yegna@cs.iitm.ernet.in Talk at NOLISP2005 April 19, 2005.

golda
Download Presentation

Separation of Multispeaker Speech Using Excitation Information

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Separation of Multispeaker Speech Using Excitation Information B.Yegnanarayana, R.Kumara Swamy and S.R.Mahadeva Prasanna Dept of Computer Science and Engineering Indian Institute of Technology Madras Chennai-600036, India yegna@cs.iitm.ernet.in Talk at NOLISP2005 April 19, 2005

  2. Multispeaker Speech SignalThree speaker case ) Ta) Microphone-1 signal b) Microphone-2 signal

  3. Multispeaker Whispered SpeechThree Speaker case Ta) Microphone-1 signal b) Microphone-2 signal

  4. Problem • Determine the # speakers • Separate individual speakers • Enhance speech of individual speakers

  5. Organization of the talk • Demo illustrating the problem of multispeaker separation • Basis: Sequences of impulses in speech production • Proposed method for speaker separation • Discussion: Scope of the present study and key ideas • Conclusions

  6. Basis for the Proposed Method of Separation • Sequences of impulses in direct speech at mic locations • No effect of channel or other degradations on the sequence • No two speakers are at the same location

  7. Proposed Method for Speaker Separation • Record multispeaker data at 2 or more mics • Compute the HE of the LP residual • Use peaks in crosscorrelation of HEs to obtain delays • Take min of shifted HEs to derive HE of desired speaker • Derive weight function and modified LP residual • Synthesize speech for each speaker

  8. LP analysis of Speech signal Ta) Speech signal b) LP residual c) Hilbert Envelope of LP residual

  9. Hilbert Envelope (HE) Ta) HE of microphone-1 signal b) HE of microphone-2 signal

  10. Cross-Correlation of Hilbert Envelopes

  11. Time-delay estimation (b) Time delay and normalized # samples (a) Peaks in the crosscorrelation plots

  12. Processing HE using time-delay Ta) HE of mic-1 signal b), c) , d) Min(HE1,HE2) emphasizing excitation information of Speaker 1,2 and 3, respectively

  13. Results of Separation a)LP residual of mic-1 signal b), c) and d) modified residual of sp1, sp2 Sp3 e), f) and g) Speech signals after separation

  14. Demo of Speaker EnhancementThree speaker case ( a) b) b) a a) Microphone-1 speech signal b) Microphone-2 speech signal

  15. Demo of Speaker Enhancemnt a) Speaker 1 b) Speaker 2 c) Speaker 3

  16. Summary • Number of speakers (whispered), speaker separation (2 mics), speech enhancement (> 2 mics) • Only speaker separation is addressed • Significance of HE for delay estimation and speaker separation • Conclusions • Need to improve the quality of enhanced speech signals • Need more microphones for data collection • Need to deal with moving speaker and variable # speakers

  17. Thank you very much for your attention

More Related