This letter proposes a perceptual metric for speech quality evaluation, which is suitable, as a loss function, for training deep learning methods. This metric, derived from the perceptual evaluation of the speech quality algorithm, is computed in a per-frame basis and from the power spectra of the reference and processed speech signal. Thus, two disturbance terms, which account for distortion once auditory masking and threshold effects are factored in, amend the mean square error (MSE) loss function by introducing perceptual criteria based on human psychoacoustics. The proposed loss function is evaluated for noisy speech enhancement with deep neural networks. Experimental results show that our metric achieves significant gains in speech quality (evaluated using an objective metric and a listening test) when compared to using MSE or other perceptual-based loss functions from the literature.

This review summarises the status of silent speech interface (SSI) research. SSIs rely on non-acoustic biosignals generated by the human body during speech production to enable communication whenever normal verbal communication is not possible or not desirable. In this review, we focus on the first case and present latest SSI research aimed at providing new alternative and augmentative communication methods for persons with severe speech disorders. SSIs can employ a variety of biosignals to enable silent communication, such as electrophysiological recordings of neural activity, electromyographic (EMG) recordings of vocal tract movements or the direct tracking of articulator movements using imaging techniques. Depending on the disorder, some sensing techniques may be better suited than others to capture speech-related information. For instance, EMG and imaging techniques are well suited for laryngectomised patients, whose vocal tract remains almost intact but are unable to speak after the removal of the vocal folds, but fail for severely paralysed individuals. From the biosignals, SSIs decode the intended message, using automatic speech recognition or speech synthesis algorithms. Despite considerable advances in recent years, most present-day SSIs have only been validated in laboratory settings for healthy users. Thus, as discussed in this paper, a number of challenges remain to be addressed in future research before SSIs can be promoted to real-world applications. If these issues can be addressed successfully, future SSIs will improve the lives of persons with severe speech impairments by restoring their communication capabilities.

Despite there being a clear evidence for top-down (e.g., attentional) effects in biological spatial hearing, relatively few machine hearing systems exploit the top-down model-based knowledge in sound localization. This paper addresses this issue by proposing a novel framework for the binaural sound localization that combines the model-based information about the spectral characteristics of sound sources and deep neural networks (DNNs). A target source model and a background source model are first estimated during a training phase using spectral features extracted from sound signals in isolation. When the identity of the background source is not available, a universal background model can be used. During testing, the source models are used jointly to explain the mixed observations and improve the localization process by selectively weighting source azimuth posteriors output by a DNN-based localization system. To address the possible mismatch between the training and testing, a model adaptation process is further employed the on-the-fly during testing, which adapts the background model parameters directly from the noisy observations in an iterative manner. The proposed system, therefore, combines the model-based and data-driven information flow within a single computational framework. The evaluation task involved localization of a target speech source in the presence of an interfering source and room reverberation. Our experiments show that by exploiting the model-based information in this way, the sound localization performance can be improved substantially under various noisy and reverberant conditions.

This paper describes a technique that generates speech acoustics from articulator movements. Our motivation is to help people who can no longer speak following laryngectomy, a procedure that is carried out tens of thousands of times per year in the Western world. Our method for sensing articulator movement, permanent magnetic articulography, relies on small, unobtrusive magnets attached to the lips and tongue. Changes in magnetic field caused by magnet movements are sensed and form the input to a process that is trained to estimate speech acoustics. In the experiments reported here this “Direct Synthesis” technique is developed for normal speakers, with glued-on magnets, allowing us to train with parallel sensor and acoustic data. We describe three machine learning techniques for this task, based on Gaussian mixture models, deep neural networks, and recurrent neural networks (RNNs). We evaluate our techniques with objective acoustic distortion measures and subjective listening tests over spoken sentences read from novels (the CMU Arctic corpus). Our results show that the best performing technique is a bidirectional RNN (BiRNN), which employs both past and future contexts to predict the acoustics from the sensor data. BiRNNs are not suitable for synthesis in real time but fixed-lag RNNs give similar results and, because they only look a little way into the future, overcome this problem. Listening tests show that the speech produced by this method has a natural quality that preserves the identity of the speaker. Furthermore, we obtain up to 92% intelligibility on the challenging CMU Arctic material. To our knowledge, these are the best results obtained for a silent-speech system without a restricted vocabulary and with an unobtrusive device that delivers audio in close to real time. This work promises to lead to a technology that truly will give people whose larynx has been removed their voices back.

HighlightsThis paper introduces a 'Silent Speech Interface' with the potential to restore the power of speech to people who have completely lost their voices.Small, unobtrusive magnets are attached to the lips and tongues and changes in magnetic field are sensed as the 'speaker' mouths what s/he wants to say.The sensor data is transformed to acoustic data by a speaker-dependent, learned transformation over parallel acoustic and sensor data.The machine learning technique used here is Mixture of Factor Analysis.Results are presented for 3 speakers which demonstrate that the SSI is capable of producing 'speech' which is both intelligible and natural. In this paper we present a silent speech interface (SSI) system aimed at restoring speech communication for individuals who have lost their voice due to laryngectomy or diseases affecting the vocal folds. In the proposed system, articulatory data captured from the lips and tongue using permanent magnet articulography (PMA) are converted into audible speech using a speaker-dependent transformation learned from simultaneous recordings of PMA and audio signals acquired before laryngectomy. The transformation is represented using a mixture of factor analysers, which is a generative model that allows us to efficiently model non-linear behaviour and perform dimensionality reduction at the same time. The learned transformation is then deployed during normal usage of the SSI to restore the acoustic speech signal associated with the captured PMA data. The proposed system is evaluated using objective quality measures and listening tests on two databases containing PMA and audio recordings for normal speakers. Results show that it is possible to reconstruct speech from articulator movements captured by an unobtrusive technique without an intermediate recognition step. The SSI is capable of producing speech of sufficient intelligibility and naturalness that the speaker is clearly identifiable, but problems remain in scaling up the process to function consistently for phonetically rich vocabularies.

Biometric systems are exposed to spoofing attacks which may compromise their security, and voice biometrics based on automatic speaker verification (ASV), is no exception. To increase the robustness against such attacks, anti-spoofing systems have been proposed for the detection of replay, synthesis and voice conversion-based attacks. However, most proposed anti-spoofing techniques are loosely integrated with the ASV system. In this work, we develop a new integration neural network which jointly processes the embeddings extracted from ASV and anti-spoofing systems in order to detect both zero-effort impostors and spoofing attacks. Moreover, we propose a new loss function based on the minimization of the area under the expected (AUE) performance and spoofability curve (EPSC), which allows us to optimize the integration neural network on the desired operating range in which the biometric system is expected to work. To evaluate our proposals, experiments were carried out on the recent ASVspoof 2019 corpus, including both logical access (LA) and physical access (PA) scenarios. The experimental results show that our proposal clearly outperforms some well-known techniques based on the integration at the score- and embedding-level. Specifically, our proposal achieves up to 23.62% and 22.03% relative equal error rate (EER) improvement over the best performing baseline in the LA and PA scenarios, respectively, as well as relative gains of 27.62% and 29.15% on the AUE metric.