Robust speaker verification via fusion of speech and lip modalities

This paper investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. It has been previously shown in our own work, and in the work of others, that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms the performance of either sub-system. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise

The use of temporal speech and lip information for multi-modal speaker identification via multi-stream HMMs

Investigates the use of temporal lip information, in conjunction with speech information, for robust, text-dependent speaker identification. We propose that significant speaker-dependent information can be obtained from moving lips, enabling speaker recognition systems to be highly robust in the presence of noise. The fusion structure for the audio and visual information is based around the use of multi-stream hidden Markov models (MSHMM), with audio and visual features forming two independent data streams. Recent work with multi-modal MSHMMs has been performed successfully for the task of speech recognition. The use of temporal lip information for speaker identification has been performed previously (T.J. Wark et al., 1998), however this has been restricted to output fusion via single-stream HMMs. We present an extension to this previous work, and show that a MSHMM is a valid structure for multi-modal speaker identification

The use of speech and lip modalities for robust speaker verification under adverse conditions

Investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. We have previously shown (Int. Conf. on Acoustics, Speech and Signal Proc., vol. 6, pp. 3693-3696, May 1998) that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms either subsystem individually. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise

Speech interference and transmission on residential balconies with road traffic noise

Balcony acoustic treatments can mitigate the effects of community road traffic noise. To further investigate, a theoretical study into the effects of balcony acoustic treatment combinations on speech interference and transmission is conducted for various street geometries. Nine different balcony types are investigated using a combined specular and diffuse reflection computer model. Diffusion in the model is calculated using the radiosity technique. The balcony types include a standard balcony with or without a ceiling and with various combinations of parapet, ceiling absorption and ceiling shield. A total of 70 balcony and street geometrical configurations are analyzed with each balcony type, resulting in 630 scenarios. In each scenario the reverberation time, speech interference level (SIL) and speech transmission index (STI) are calculated. These indicators are compared to determine trends based on the effects of propagation path, inclusion of opposite buildings and difference with a reference position outside the balcony. The results demonstrate trends in SIL and STI with different balcony types. It is found that an acoustically treated balcony reduces speech interference. A parapet provides the largest improvement, followed by absorption on the ceiling. The largest reductions in speech interference arise when a combination of balcony acoustic treatments are applied.

Cortical processing of speech and non-speech sounds in adults and newborns

Comprehension of a complex acoustic signal - speech - is vital for human communication, with numerous brain processes required to convert the acoustics into an intelligible message. In four studies in the present thesis, cortical correlates for different stages of speech processing in a mature linguistic system of adults were investigated. In two further studies, developmental aspects of cortical specialisation and its plasticity in adults were examined. In the present studies, electroencephalographic (EEG) and magnetoencephalographic (MEG) recordings of the mismatch negativity (MMN) response elicited by changes in repetitive unattended auditory events and the phonological mismatch negativity (PMN) response elicited by unexpected speech sounds in attended speech inputs served as the main indicators of cortical processes. Changes in speech sounds elicited the MMNm, the magnetic equivalent of the electric MMN, that differed in generator loci and strength from those elicited by comparable changes in non-speech sounds, suggesting intra- and interhemispheric specialisation in the processing of speech and non-speech sounds at an early automatic processing level. This neuronal specialisation for the mother tongue was also reflected in the more efficient formation of stimulus representations in auditory sensory memory for typical native-language speech sounds compared with those formed for unfamiliar, non-prototype speech sounds and simple tones. Further, adding a speech or non-speech sound context to syllable changes was found to modulate the MMNm strength differently in the left and right hemispheres. Following the acoustic-phonetic processing of speech input, phonological effort related to the selection of possible lexical (word) candidates was linked with distinct left-hemisphere neuronal populations. In summary, the results suggest functional specialisation in the neuronal substrates underlying different levels of speech processing. Subsequently, plasticity of the brain's mature linguistic system was investigated in adults, in whom representations for an aurally-mediated communication system, Morse code, were found to develop within the same hemisphere where representations for the native-language speech sounds were already located. Finally, recording and localization of the MMNm response to changes in speech sounds was successfully accomplished in newborn infants, encouraging future MEG investigations on, for example, the state of neuronal specialisation at birth.

Compressive Sensing For Sparsely Excited Speech Signals

Compressive sensing (CS) has been proposed for signals with sparsity in a linear transform domain. We explore a signal dependent unknown linear transform, namely the impulse response matrix operating on a sparse excitation, as in the linear model of speech production, for recovering compressive sensed speech. Since the linear transform is signal dependent and unknown, unlike the standard CS formulation, a codebook of transfer functions is proposed in a matching pursuit (MP) framework for CS recovery. It is found that MP is efficient and effective to recover CS encoded speech as well as jointly estimate the linear model. Moderate number of CS measurements and low order sparsity estimate will result in MP converge to the same linear transform as direct VQ of the LP vector derived from the original signal. There is also high positive correlation between signal domain approximation and CS measurement domain approximation for a large variety of speech spectra.

GMM based Bayesian approach to speech enhancement in signal transform domain

Considering a general linear model of signal degradation, by modeling the probability density function (PDF) of the clean signal using a Gaussian mixture model (GMM) and additive noise by a Gaussian PDF, we derive the minimum mean square error (MMSE) estimator. The derived MMSE estimator is non-linear and the linear MMSE estimator is shown to be a special case. For speech signal corrupted by independent additive noise, by modeling the joint PDF of time-domain speech samples of a speech frame using a GMM, we propose a speech enhancement method based on the derived MMSE estimator. We also show that the same estimator can be used for transform-domain speech enhancement.

A speech-music discriminator using HILN model based features

We propose a simple speech music discriminator that uses features based on HILN(Harmonics, Individual Lines and Noise) model. We have been able to test the strength of the feature set on a standard database of 66 files and get an accuracy of around 97%. We also have tested on sung queries and polyphonic music and have got very good results. The current algorithm is being used to discriminate between sung queries and played (using an instrument like flute) queries for a Query by Humming(QBH) system currently under development in the lab.

Dynamic programming based optimum non-uniform samples for speech reconstruction and coding

Non-uniform sampling of a signal is formulated as an optimization problem which minimizes the reconstruction signal error. Dynamic programming (DP) has been used to solve this problem efficiently for a finite duration signal. Further, the optimum samples are quantized to realize a speech coder. The quantizer and the DP based optimum search for non-uniform samples (DP-NUS) can be combined in a closed-loop manner, which provides distinct advantage over the open-loop formulation. The DP-NUS formulation provides a useful control over the trade-off between bitrate and performance (reconstruction error). It is shown that 5-10 dB SNR improvement is possible using DP-NUS compared to extrema sampling approach. In addition, the close-loop DP-NUS gives a 4-5 dB improvement in reconstruction error.

Speech segmentation using extrema based signal track length measure

We introduce a novel temporal feature of a signal, namely extrema-based signal track length (ESTL) for the problem of speech segmentation. We show that ESTL measure is sensitive to both amplitude and frequency of the signal. The short-time ESTL (ST_ESTL) shows a promising way to capture the significant segments of speech signal, where the segments correspond to acoustic units of speech having distinct temporal waveforms. We compare ESTL based segmentation with ML and STM methods and find that it is as good as spectral feature based segmentation, but with lesser computational complexity.

RIESZ-TRANSFORM-BASED DEMODULATION OF NARROWBAND SPECTROGRAMS OF VOICED SPEECH

Narrowband spectrograms of voiced speech can be modeled as an outcome of two-dimensional (2-D) modulation process. In this paper, we develop a demodulation algorithm to estimate the 2-D amplitude modulation (AM) and carrier of a given spectrogram patch. The demodulation algorithm is based on the Riesz transform, which is a unitary, shift-invariant operator and is obtained as a 2-D extension of the well known 1-D Hilbert transform operator. Existing methods for spectrogram demodulation rely on extension of sinusoidal demodulation method from the communications literature and require precise estimate of the 2-D carrier. On the other hand, the proposed method based on Riesz transform does not require a carrier estimate. The proposed method and the sinusoidal demodulation scheme are tested on real speech data. Experimental results show that the demodulated AM and carrier from Riesz demodulation represent the spectrogram patch more accurately compared with those obtained using the sinusoidal demodulation. The signal-to-reconstruction error ratio was found to be about 2 to 6 dB higher in case of the proposed demodulation approach.