1,721,133 research outputs found
Sparse Parametric Modeling of the Early Part of Acoustic Impulse Responses
Full text linkPublication in the conference proceedings of EUSIPCO, Kos island, Greece, 201
Glottal-synchronous speech processing
Full text linkGlottal-synchronous speech processing is a field of speech science where the pseudoperiodicity
of voiced speech is exploited. Traditionally, speech processing involves segmenting
and processing short speech frames of predefined length; this may fail to exploit the inherent
periodic structure of voiced speech which glottal-synchronous speech frames have
the potential to harness. Glottal-synchronous frames are often derived from the glottal
closure instants (GCIs) and glottal opening instants (GOIs).
The SIGMA algorithm was developed for the detection of GCIs and GOIs from
the Electroglottograph signal with a measured accuracy of up to 99.59%. For GCI and
GOI detection from speech signals, the YAGA algorithm provides a measured accuracy
of up to 99.84%. Multichannel speech-based approaches are shown to be more robust to
reverberation than single-channel algorithms.
The GCIs are applied to real-world applications including speech dereverberation,
where SNR is improved by up to 5 dB, and to prosodic manipulation where the importance
of voicing detection in glottal-synchronous algorithms is demonstrated by subjective
testing. The GCIs are further exploited in a new area of data-driven speech modelling,
providing new insights into speech production and a set of tools to aid deployment into
real-world applications. The technique is shown to be applicable in areas of speech coding,
identification and artificial bandwidth extension of telephone speec
Polynomial matrix eigenvalue decomposition of spherical harmonics for speech enhancement
No full textSpeech enhancement algorithms using polynomialmatrixeigenvalue decomposition (PEVD) have been shown to be effective for noisy and reverberant speech. However, these algorithms do not scale well in complexity with the number of channels used in the processing. For a spherical microphone array sampling an order-limited sound field, the spherical harmonics provide a compact representation of the microphone signals in the form of eigenbeams. We propose a PEVD algorithm that uses only the lower dimension eigenbeams for speech enhancement at a significantly lower computation cost. The proposed algorithm is shown to significantly reduce complexity while maintaining full performance. Informal listening examples have also indicated that the processing does not introduce any noticeable artefacts
Polynomial matrix eigenvalue decomposition-based source separation using informed spherical microphone arrays
No full textAudio source separation is essential for many applications such as hearing aids, telecommunications, and robot audition. Subspace decomposition approaches using polynomial matrix eigenvalue decomposition (PEVD) algorithms applied to the microphone signals, or lower-dimension eigenbeams for spherical microphone arrays, are effective for speech enhancement. In this work, we extend the work from speech enhancement and propose a PEVD subspace algorithm that uses eigenbeams for source separation. The proposed PEVD-based source separation approach performs comparably with state-of-the-art algorithms, such as those based on independent component analysis (ICA) and multi-channel non-negative matrix factorization (MNMF). Informal listening examples also indicate that our method does not introduce any audible artifacts.<br/
End-to-end classification of reverberant rooms using DNNs
Full text linkReverberation is present in our workplaces, our homes, concert halls and theatres. This article investigates how deep learning can use the effect of reverberation on speech to classify a recording in terms of the room in which it was recorded. Existing approaches in the literature rely on domain expertise to manually select acoustic parameters as inputs to classifiers. Estimation of these parameters from reverberant speech is adversely affected by estimation errors, impacting the classification accuracy. In order to overcome the limitations of previously proposed methods, this paper shows how DNNs can perform the classification by operating directly on reverberant speech spectra and a CRNN with an attention-mechanism is proposed for the task. The relationship is investigated between the reverberant speech representations learned by the DNNs and acoustic parameters. For evaluation, AIRs are used from the ACE-challenge dataset that were measured in 7 real rooms. The classification accuracy of the CRNN classifier in the experiments is 78% when using 5 hours of training data and 90% when using 10 hours.</p
Multiple hypothesis tracking for overlapping speaker segmentation
Full text linkSpeaker segmentation is an essential part of any diarization system.Applications of diarization include tasks such as speaker indexing, improving automatic speech recognition (ASR) performance and making single speaker-based algorithms available for use in multi-speaker environments.This paper proposes a multiple hypothesis tracking (MHT) method that exploits the harmonic structure associated with the pitch in voiced speech in order to segment the onsets and end-points of speech from multiple, overlapping speakers. The proposed method is evaluated against a segmentation system from the literature that uses a spectral representation and is based on employing bidirectional long short term memory networks (BLSTM). The proposed method is shown to achieve comparable performance for segmenting overlapping speakers only using the pitch harmonic information in the MHT framework
Speech dereverberation performance of a polynomial-EVD subspace approach
No full textThe degradation of speech arising from additive background noise and reverberation affects the performance of important speech applications such as telecommunications, hearing aids, voice-controlled systems and robot audition. In this work, we focus on dereverberation. It is shown that the parameterized polynomial matrix eigenvalue decomposition (PEVD)-based speech enhancement algorithm exploits the lack of correlation between speech and the late reflections to enhance the speech component associated with the direct path and early reflections. The algorithm’s performance is evaluated using simulations involving measured acoustic impulse responses and noise from the ACE corpus. The simulations and informal listening examples have indicated that the PEVD-based algorithm performs dereverberation over a range of SNRs without introducing any noticeable processing artefacts
Signal compaction using polynomial EVD for spherical array processing with applications
No full textMulti-channel signals captured by spatially separated sensors often contain a high level of data redundancy. A compact signal representation enables more efficient storage and processing, which has been exploited for data compression, noise reduction, and speech and image coding. This paper focuses on the compact representation of speech signals acquired by spherical microphone arrays. A polynomial matrix eigenvalue decomposition (PEVD) can spatially decorrelate signals over a range of time lags and is known to achieve optimum multi-channel data compaction. However, the complexity of PEVD algorithms scales at best cubically with the number of channel signals, e.g., the number of microphones comprised in a spherical array used for processing. In contrast, the spherical harmonic transform (SHT) provides a compact spatial representation of the 3-dimensional sound field measured by spherical microphone arrays, referred to as eigenbeam signals, at a cost that rises only quadratically with the number of microphones. Yet, the SHT's spatially orthogonal basis functions cannot completely decorrelate sound field components over a range of time lags. In this work, we propose to exploit the compact representation offered by the SHT to reduce the number of channels used for subsequent PEVD processing. In the proposed framework for signal representation, we show that the diagonality factor improves by up to 7 dB over the microphone signal representation with a significantly lower computation cost. Moreover, when applying this framework to speech enhancement and source separation, the proposed method improves metrics known as short-time objective intelligibility (STOI) and source-to-distortion ratio (SDR) by up to 0.2 and 20 dB, respectively.</p
PEVD-Based Speech Enhancement in Reverberant Environments
No full textThe enhancement of noisy speech is important for applications involving human-to-human interactions, such as telecommunications and hearing aids, as well as human-to-machine interactions, such as voice-controlled systems and robot audition. In this work, we focus on reverberant environments. It is shown that, by exploiting the lack of correlation between speech and the late reflections, further noise reduction can be achieved. This is verified using simulations involving actual acoustic impulse responses and noise from the ACE corpus. The simulations show that even without using a noise estimator, our proposed method simultaneously achieves noise reduction, and enhancement of speech quality and intelligibility, in reverberant environments over a wide range of SNRs. Furthermore, informal listening examples highlight that our approach does not introduce any significant processing artefacts such as musical noise
Discriminative feature domains for reverberant acoustic environments
No full textSeveral speech processing and audio data-mining applications rely on a description of the acoustic environment as a feature vector for classification. The discriminative properties of the feature domain play a crucial role in the effectiveness of these methods. In this work, we consider three environment identification tasks and the task of acoustic model selection for speech recognition. A set of acoustic parameters and Machine Learning algorithms for feature selection are used and an analysis is performed on the resulting feature domains for each task. In our experiments, a classification accuracy of 100% is achieved for the majority of tasks and the Word Error Rate is reduced by 20.73 percentage points for Automatic Speech Recognition when using the resulting domains. Experimental results indicate a significant dissimilarity in the parameter choices for the composition of the domains, which highlights the importance of the feature selection process for individual applications.</p
- …
