Results
- Showing results for:
- Reset all filters
Search results
-
Journal articled'Olne E, Moore AH, Naylor PA, et al., 2024, , IEEE OPEN JOURNAL OF SIGNAL PROCESSING, Vol: 5, Pages: 374-382
-
Conference paperSanguedolce G, Naylor PA, Geranmayeh F, 2023, , 5th Clinical Natural Language Processing Workshop, Publisher: Association for Computational Linguistics, Pages: 182-190
Post-stroke speech and language deficits (aphasia) significantly impact patients' quality of life. Many with mild symptoms remain undiagnosed, and the majority do not receive the intensive doses of therapy recommended, due to healthcare costs and/or inadequate services. Automatic Speech Recognition (ASR) may help overcome these difficulties by improving diagnostic rates and providing feedback during tailored therapy. However, its performance is often unsatisfactory due to the high variability in speech errors and scarcity of training datasets. This study assessed the performance of Whisper, a recently released end-to-end model, in patients with post-stroke aphasia (PWA). We tuned its hyperparameters to achieve the lowest word error rate (WER) on aphasic speech. WER was significantly higher in PWA compared to age-matched controls (10.3% vs 38.5%, p < 0.001). We demonstrated that worse WER was related to the more severe aphasia as measured by expressive (overt naming, and spontaneous speech production) and receptive (written and spoken comprehension) language assessments. Stroke lesion size did not affect the performance of Whisper. Linear mixed models accounting for demographic factors, therapy duration, and time since stroke, confirmed worse Whisper performance with left hemispheric frontal lesions. We discuss the implications of these findings for how future ASR can be improved in PWA.
-
Conference paperMcKnight S, Hogg AOT, Neo VW, et al., 2022, , APSIPA 2022, Publisher: IEEE, Pages: 394-401
Human-based speaker diarization experiments were carried out on a five-minute extract of a typical AMI corpus meeting to see how much variance there is in human reviews based on hearing only and to compare with state-of-the-art diarization systems on the same extract. There are three distinct experiments: (a) one with no prior information; (b) one with the ground truth speech activity detection (GT-SAD); and (c) one with the blank ground truth labels (GT-labels). The results show that most human reviews tend to be quite similar, albeit with some outliers, but the choice of GT-labels can make a dramatic difference to scored performance. Using the GT-SAD provides a big advantage and improves human review scores substantially, though small differences in the GT-SAD used can have a dramatic effect on results. The use of forgiveness collars is shown to be unhelpful. The results show that state-of-the-art systems can outperform the best human reviews when no prior information is provided. However, the best human reviews still outperform state-of-the-art systems when starting from the GT-SAD.
-
Conference paperNeo VW, D'Olne E, Moore AH, et al., 2022, , International Workshop on Acoustic Signal Enhancement (IWAENC), Publisher: IEEE, Pages: 1-5
Array processing is widely used in many speech applications involving multiple microphones. These applications include automaticspeech recognition, robot audition, telecommunications, and hearing aids. A spatio-temporal filter for the array allows signals fromdifferent microphones to be combined desirably to improve the application performance. This paper will analyze and visually interpretthe eigenvector beamformers designed by the polynomial eigenvaluedecomposition (PEVD) algorithm, which are suited for arbitrary arrays. The proposed fixed PEVD beamformers are lightweight, withan average filter length of 114 and perform comparably to classicaldata-dependent minimum variance distortionless response (MVDR)and linearly constrained minimum variance (LCMV) beamformersfor the separation of sources closely spaced by 5 degrees.
-
Conference paperNeo VW, Weiss S, McKnight S, et al., 2022, , International Workshop on Acoustic Signal Enhancement (IWAENC), Publisher: IEEE, Pages: 1-5
Voice activity detection (VAD) algorithms are essential for many speech processing applications, such as speaker diarization, automatic speech recognition, speech enhancement, and speech coding. With a good VAD algorithm, non-speech segments can be excluded to improve the performance and computation of these applications. In this paper, we propose a polynomial eigenvalue decomposition-based target-speaker VAD algorithm to detect unseen target speakers in the presence of competing talkers. The proposed approach uses frame-based processing to compute the syndrome energy, used for testing the presence or absence of a target speaker. The proposed approach is consistently among the best in F1 and balanced accuracy scores over the investigated range of signal to interference ratio (SIR) from -10 dB to 20 dB.
-
Conference paperTokala V, Brookes M, Naylor P, 2022, , International Workshop on Acoustic Signal Enhancement (IWAENC) 2022, Publisher: IEEE, Pages: 1-5
STOI-optimal masking has been previously proposed and developed for single-channel speech enhancement. In this paper, we consider the extension to the task of binaural speech enhancement in which the spatial information is known to be important to speech understanding and therefore should bepreserved by the enhancement processing. Masks are estimated for each of the binaural channels individually and a ‘better-ear listening’ mask is computed by choosing the maximum of the two masks. The estimated mask is used to supply probability information about the speech presence in eachtime-frequency bin to an Optimally-modified Log Spectral Amplitude (OM-LSA) enhancer. We show that using the pro-posed method for binaural signals with a directional noise not only improves the SNR of the noisy signal but also preserves the binaural cues and intelligibility.
-
Conference paperMcKnight S, Hogg A, Neo V, et al., 2022,
A study of salient modulation domain features for speaker identification
, Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Publisher: IEEE, Pages: 705-712This paper studies the ranges of acoustic andmodulation frequencies of speech most relevant for identifyingspeakers and compares the speaker-specific information presentin the temporal envelope against that present in the temporalfine structure. This study uses correlation and feature importancemeasures, random forest and convolutional neural network mod-els, and reconstructed speech signals with specific acoustic and/ormodulation frequencies removed to identify the salient points. Itis shown that the range of modulation frequencies associated withthe fundamental frequency is more important than the 1-16 Hzrange most commonly used in automatic speech recognition, andthat the 0 Hz modulation frequency band contains significantspeaker information. It is also shown that the temporal envelopeis more discriminative among speakers than the temporal finestructure, but that the temporal fine structure still contains usefuladditional information for speaker identification. This researchaims to provide a timely addition to the literature by identifyingspecific aspects of speech relevant for speaker identification thatcould be used to enhance the discriminant capabilities of machinelearning models.
-
Journal articleGreen T, Hilkhuysen G, Huckvale M, et al., 2022, , Trends in Hearing, Vol: 26, Pages: 1-16, ISSN: 2331-2165
A signal processing approach combining beamforming with mask-informed speech enhancement was assessed by measuring sentence recognition in listeners with mild-to-moderate hearing impairment in adverse listening conditions that simulated the output of behind-the-ear hearing aids in a noisy classroom. Two types of beamforming were compared: binaural, with the two microphones of each aid treated as a single array, and bilateral, where independent left and right beamformers were derived. Binaural beamforming produces a narrower beam, maximising improvement in signal-to-noise ratio (SNR), but eliminates the spatial diversity that is preserved in bilateral beamforming. Each beamformer type was optimised for the true target position and implemented with and without additional speech enhancement in which spectral features extracted from the beamformer output were passed to a deep neural network trained to identify time-frequency regions dominated by target speech. Additional conditions comprising binaural beamforming combined with speech enhancement implemented using Wiener filtering or modulation-domain Kalman filtering were tested in normally-hearing (NH) listeners. Both beamformer types gave substantial improvements relative to no processing, with significantly greater benefit for binaural beamforming. Performance with additional mask-informed enhancement was poorer than with beamforming alone, for both beamformer types and both listener groups. In NH listeners the addition of mask-informed enhancement produced significantly poorer performance than both other forms of enhancement, neither of which differed from the beamformer alone. In summary, the additional improvement in SNR provided by binaural beamforming appeared to outweigh loss of spatial information, while speech understanding was not further improved by the mask-informed enhancement method implemented here.
-
Conference paperSathyapriyan V, Pedersen MS, Ostergaard J, et al., 2022, , 17th International Workshop on Acoustic Signal Enhancement (IWAENC), Publisher: IEEE, ISSN: 2639-4316
-
Conference paperGuiraud P, Moore AH, Vos RR, et al., 2022, , 17th International Workshop on Acoustic Signal Enhancement (IWAENC), Publisher: IEEE, ISSN: 2639-4316
-
Conference paperD'Olne E, Moore A, Naylor P, 2021, , European Signal Processing Conference (EUSIPCO), Publisher: IEEE, Pages: 1105-1109
Beamforming techniques for hearing aid applications are often evaluated using behind-the-ear (BTE) devices. However, the growing number of wearable devices with microphones has made it possible to consider new geometries for microphone array beamforming. In this paper, we examine the effect of array location and geometry on the performance of binaural minimum power distortionless response (BMPDR) beamformers. In addition to the classical adaptive BMPDR, we evaluate the benefit of a recently-proposed method that estimates the sample covariance matrix using a compact model. Simulation results show that using a chest-mounted array reduces noise by an additional 1.3~dB compared to BTE hearing aids. The compact model method is found to yield higher predicted intelligibility than adaptive BMPDR beamforming, regardless of the array geometry.
-
Conference paperHogg AOT, Neo VW, Weiss S, et al., 2021, , 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Publisher: IEEE, Pages: 326-330
-
Conference paperHogg AOT, Evers C, Naylor PA, 2021, , ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 26-30
-
Conference paperMoore A, Vos R, Naylor P, et al., 2021, , ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Publisher: IEEE, ISSN: 0736-7791
Multichannel acoustic signal processing is predicated on the fact that the inter channel relationships between the received signals can be exploited to infer information about the acoustic scene. Recently there has been increasing interest in algorithms which are applicable in dynamic scenes, where the source(s) and/or microphone array may be moving. Simulating such scenes has particular challenges which are exacerbated when real-time, listener-in-the-loop evaluation of algorithms is required. This paper considers candidate pipelines for simulating the array response to a set of point/image sources in terms of their accuracy, scalability and continuity. Anew approach, in which the filter kernels are obtained using principal component analysis from time-aligned impulse responses, is proposed. When the number of filter kernels is≤40the new approach achieves more accurate simulation than competing methods.
-
Journal articleHogg A, Evers C, Moore A, et al., 2021, , IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol: 29, Pages: 1479-1490, ISSN: 2329-9290
This paper demonstrates how the harmonic structure of voiced speech can be exploited to segment multiple overlapping speakers in a speaker diarization task. We explore how a change in the speaker can be inferred from a change in pitch. We show that voiced harmonics can be useful in detecting when more than one speaker is talking, such as during overlapping speaker activity. A novel system is proposed to track multiple harmonics simultaneously, allowing for the determination of onsets and end-points of a speaker’s utterance in the presence of an additional active speaker. This system is bench-marked against a segmentation system from the literature that employs a bidirectional long short term memory network (BLSTM) approach and requires training. Experimental results highlight that the proposed approach outperforms the BLSTM baseline approach by 12.9% in terms of HIT rate for speaker segmentation. We also show that the estimated pitch tracks of our system can be used as features to the BLSTM to achieve further improvements of 1.21% in terms of coverage and 2.45% in terms of purity
-
Journal articleHafezi S, Moore A, Naylor P, 2021, , Journal of the Acoustical Society of America, Vol: 149, ISSN: 0001-4966
A conventional approach to wideband multi-source (MS) direction-of-arrival (DOA) estimation is to perform single source (SS) DOA estimation in time-frequency (TF) bins for which a SS assumption is valid. Such methods use the W-disjoint orthogonality (WDO) assumption due to the speech sparseness. As the number of sources increases, the chance of violating the WDO assumption increases. As shown in the challenging scenarios with multiple simultaneously active sources over a short period of time masking each other, it is possible for a strongly masked source (due to inconsistency of activity or quietness) to be rarely dominant in a TF bin. SS-based DOA estimators fail in the detection or accurate localization of masked sources in such scenarios. Two analytical approaches are proposed for narrowband DOA estimation based on the MS assumption in a bin in the spherical harmonic domain. In the first approach, eigenvalue decomposition is used to decompose a MS scenario into multiple SS scenarios, and a SS-based analytical DOA estimation is performed on each. The second approach analytically estimates two DOAs per bin assuming the presence of two active sources per bin. The evaluation validates the improvement to double accuracy and robustness to sensor noise compared to the baseline methods.
-
Conference paperMcKnight SW, Hogg AOT, Naylor PA, 2021, , 2020 28th European Signal Processing Conference (EUSIPCO), Publisher: IEEE, Pages: 381-385
-
Journal articleXue W, Moore A, Brookes D, et al., 2020, , IEEE Transactions on Audio, Speech and Language Processing, Vol: 29, Pages: 393-405, ISSN: 1558-7916
Recently we presented a modulation-domain multichannel Kalman filtering (MKF) algorithm for speech enhancement, which jointly exploits the inter-frame modulation-domain temporal evolution of speech and the inter-channel spatial correlation to estimate the clean speech signal. The goal of speech enhancement is to suppress noise while keeping the speech undistorted, and a key problem is to achieve the best trade-off between speech distortion and noise reduction. In this paper, we extend the MKF by presenting a modulation-domain parametric MKF (PMKF) which includes a parameter that enables flexible control of the speech enhancement behaviour in each time-frequency (TF) bin. Based on the decomposition of the MKF cost function, a new cost function for PMKF is proposed, which uses the controlling parameter to weight the noise reduction and speech distortion terms. An optimal PMKF gain is derived using a minimum mean squared error (MMSE) criterion. We analyse the performance of the proposed MKF, and show its relationship to the speech distortion weighted multichannel Wiener filter (SDW-MWF). To evaluate the impact of the controlling parameter on speech enhancement performance, we further propose PMKF speech enhancement systems in which the controlling parameter is adaptively chosen in each TF bin. Experiments on a publicly available head-related impulse response (HRIR) database in different noisy and reverberant conditions demonstrate the effectiveness of the proposed method.
-
Journal articleHafezi S, Moore AH, Naylor PA, 2019, , Journal of the Acoustical Society of America, Vol: 146, Pages: 4592-4603, ISSN: 0001-4966
A conventional approach to wideband multi-source (MS) direction-of-arrival (DOA) estimation is to perform single source (SS) DOA estimation in time-frequency (TF) bins for which a SS assumption is valid. The typical SS-validity confidence metrics analyse the validity of the SS assumption over a fixed-size TF region local to the TF bin. The performance of such methods degrades as the number of simultaneously active sources increases due to the associated decrease in the size of the TF regions where the SS assumption is valid. A SS-validity confidence metric is proposed that exploits a dynamic MS assumption over relatively larger TF regions. The proposed metric first clusters the initial DOA estimates (one per TF bin) and then uses the members' spatial consistency as well as its cluster's spread to weight each TF bin. Distance-based and density-based clustering are employed as two alternative approaches for clustering DOAs. A noise-robust density-based clustering is also used in an evolutionary framework to propose a method for source counting and source direction estimation. The evaluation results based on simulations and also with real recordings show that the proposed weighting strategy significantly improves the accuracy of source counting and MS DOA estimation compared to the state-of-the-art.
-
Conference paperHogg AOT, Evers C, Naylor PA, 2019, , 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Publisher: IEEE, Pages: 195-199
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.
Contact us
Address
Speech and Audio Processing Lab
CSP Group, EEE Department
³Ô¹ÏºÚÁÏ
Exhibition Road, London, SW7 2AZ, United Kingdom