| 1. |
- Ballal, Tarig, et al.
(författare)
-
A Simple and Computationally Efficient Algorithm for Real-Time Blind Source Separation of Speech Mixtures
- 2006
-
Konferensbidrag (refereegranskat)abstract
- In this paper we exploit the amplitude diversity provided by two sensors to achieve blind separation of two speech sources. We propose a simple and highly computationally efficient method for separating sources that are W-disjoint orthogonal (W-DO), that are sources whose time-frequency representations are disjoint sets. The Degenerate Unmixing and Estimation Technique (DUET), a powerful and efficient method that exploits the W-disjoint orthogonality property, requires extensive computations for maximum likehood parameter learning. Our proposed method avoids all the computations required for parameters estimation by assuming that the sources are "cross high-low diverse (CH-LD)", an assumption that is explained later and that can be satisfied exploiting the sensors settings/directions. With this assumption and the W-disjoint orthogonality property, two binary time-frequency masks that can extract the original sources from one of the two mixtures, can be constructed directly from the amplitude ratios of the time-frequency points of the two mixtures. The method works very well when tested with both artificial and real mixtures. Its performance is comparable to DUET, and it requires only 2% of the computations required by the DUET method. Moreover, it is free of convergence problems that lead to poor SIR ratios in the first parts of the signals. As with all binary masking approaches, the method suffers from artifacts that appear in the output signals.
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Cornelius, Per, et al.
(författare)
-
A Spatially Constrained Subband Beamforming Algorithm for speech enhancement
- 2004
-
Konferensbidrag (refereegranskat)abstract
- This paper discusses speech enhancement in an enclosed environment such as communication in a motorcycle helmet. A new constrained subband adaptive beamformer is proposed, which uses the concept of an earlier proposed calibrated beamformer mainly developed for a hands-free in-car environment. The highly non-stationary nature of the disturbing sound field encountered in an motorcycle helmet and the fact that the source is situated in the extreme nearfield of the array, causes the beamformer to produce an unwanted fluctuation in the output level. The spatially constrained beamformer proposed in this paper makes sure that the output maintains a constant gain, as long as the corresponding source originates from the desired location.
|
|
| 6. |
- Cornelius, Per, et al.
(författare)
-
Microphone array system for speech enhancement in a motorcycle helmet
- 2005
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- In this report a real case study of the sound environment within a helmet while driving motorcycle is investigated. A solution to perform speech enhancement is proposed for the purpose of mobile speech communication. A microphone array, mounted onto the face shield in front of the user's mouth, is used to capture the spatio-temporal properties of the acoustic wave ¯eld inside the helmet. The power of the spatially spread noise within the helmet is small when standing still while it may heavily exceed the power of the speech when driving at high speeds. This will result in dramatically reduced speech intelligibility in the communication channel. The highly dynamic noise level imposes a challenge for existing speech enhancement solutions. We propose a subband adaptive system for speech enhancement which consists of a soft constrained beamformer in cascade with a signal-to-noise ratio dependent single microphone solution. The beamformer make use of a calibration signal gathered in the actual environment from the speaker's position. This calibration procedure e±ciently captures the acoustical properties in the environment. Evaluation of the beamformer and the single microphone algorithm, both as either parts by them selves and as a cascaded structure, together with the optimal subband Wiener solution is presented. It is shown that a cascaded combination of the calibrated subband beamforming technique together with the single channel solution outperforms either one by it self, and provides near optimal results at all noise levels.
|
|
| 7. |
|
|
| 8. |
- Dam, H. Q., et al.
(författare)
-
Adaptive beamformer with recursively updated quadratic constraints
- 2003
-
Ingår i: ICICS-PCM 2003. Proceedings of the 2003 Joint Conference of the Fourth International Conference on Information, Communications and Signal Processing and Fourth Pacific-Rim Conference on Multimedia. - 0780381858 ; 1, s. 105-109
-
Konferensbidrag (refereegranskat)abstract
- A novel adaptive beamformer employing recursively updated soft constraints for acoustic speech enhancement is proposed. The beamformer operates in a subband structure to allow time-frequency operation for each channel. As such, the processing can be viewed as a combination of weighted spatial and temporal filters. The major benefit of this recursive soft constrained beamformer is that it allows the possibility of using the spectral information of the desired source to modify the soft constraint. This has clear benefits on the speech distortion of the source of interest. The novel adaptive beamformer involves continuous modification of the soft constraint by feeding back the spectral content of the estimated output speech signal. Evaluations on real car data show that the proposed algorithm significantly improves the speech quality with noise suppression levels up to 17 dB.
|
|
| 9. |
- Davis, Alan, et al.
(författare)
-
A subband space constrained beamformer incorporating voice activity detection
- 2005
-
Konferensbidrag (refereegranskat)abstract
- This paper introduces a new subband adaptive space constrained beamforming structure for use in hands-free speech enhancement applications. The scheme incorporates a space constrained source model and voice activity information through the integration of a voice activity detector (VAD). The VAD information is used to estimate noise covariance information during non-speech periods and to optimally estimate the source power spectral density (PSD), which is used to provide a spectrally optimized constraint on the source. The proposed structure is evaluated in a real car environment, yielding results which compare well to the optimal Wiener solution where full knowledge of the source is known. ©2005 IEEE.
|
|
| 10. |
- Fai, Cedric Yiu Ka, et al.
(författare)
-
A New Design Method for Broadband Microphone Arrays for Speech Input in Automobiles
- 2002
-
Ingår i: IEEE Signal Processing Letters. - : IEEE. - 1070-9908 .- 1558-2361. ; 9:7, s. 222-224
-
Tidskriftsartikel (refereegranskat)abstract
- A new design method for broadband microphone arrays is presented. Using sequences of calibration signals, the method is able to design finite-impulse response (FIR) filters with specific performance. The method can control and adjust the speech distortion, noise suppression, and echo cancellation directly. It turns out that a significantly shorter filter length can be applied to achieve better overall performance than the least-squares method or the signal-to-noise plus interference method.
|
|
