Diplophonia is a type of pathological voice in which two fundamental frequencies (fo) are present simultaneously. Specialized audio analyzers that can handle up to two fos in diplophonic voices are in their infancy. We propose the tracking of up to two fos in diplophonic voices by audio waveform modeling (AWM), which involves obtaining candidates by repetitive execution of the Viterbi algorithm, followed by waveform Fourier synthesis, and heuristic candidate selection with majority voting. Our approach is evaluated with reference fo-tracks obtained from laryngeal highspeed videos of 29 sustained phonations and compared to state-of-the-art tracking algorithms for multiple fos. An accurate and a fast variant of our algorithm are tested. The median error rate of the accurate variant is 6.52%, whereas the most accurate benchmark achieves 11.11%. The fast variant is more than twice as fast as the fastest relevant benchmark, and the median error rate is 9.52%. Furthermore, illustrative results of connected speech analysis are reported. Our approach may help to improve detection and analysis of diplophonia in clinical research and practice, as well as to advance synthesis of disordered voices.

The aim of this work is the estimation of respiratory flow from lung sound recordings, i.e. acoustic airflow estimation. With a 16-channel lung sound recording device, we simultaneously record the respiratory flow and the lung sounds on the posterior chest from six lung-healthy subjects in supine position. For the recordings of four selected sensor positions, we extract linear frequency cepstral coefficient (LFCC) features and map these on the airflow signal. We use multivariate polynomial regression to fit the features to the airflow signal. Compared to most of the previous approaches, the proposed method uses lung sounds instead of trachea sounds. Furthermore, our method masters the estimation of the airflow without prior knowledge of the respiratory phase, i.e. no additional algorithm for phase detection is required. Another benefit is the avoidance of time-consuming calibration. In experiments, we evaluate the proposed method for various selections of sensor positions in terms of mean squared error (MSE) between estimated and actual airflow. Moreover, we show the accuracy of the method regarding a frame-based breathing-phase detection.

We introduce a new and intuitive algorithm to characterize and localize multiple harmonic sources intersecting in the spatial and frequency domains. It jointly estimates their fundamental frequencies, their respective amplitudes, and their directions of arrival based on an intelligent non-parametric signal representation. To obtain these parameters, we first apply variable-scale sampling on unbiased cross-correlation functions between pairs of microphone signals to generate a joint parameter space. Then, we employ a multidimensional maxima detector to represent the parameters in a sparse joint parameter space. In comparison to others, our algorithm solves the issue of pitch-period doubling when using cross-correlation functions, it estimates multiple harmonic sources with a signal power smaller than the signal power of the dominant harmonic source, and it associates the estimated parameters to their corresponding sources in a multidimensional sparse joint parameter space, which can be directly fed into a tracker. We tested our algorithm and three others on synthetic data and speech data recorded in a real reverberant environment and evaluated their performance by employing the joint recall measure, the root-mean-square error, and the cumulative distribution function of fundamental frequencies and directions of arrival. The evaluations show promising results: Our algorithm outperforms the others in terms of the joint recall measure, and it can achieve root-mean-square errors of 1 Hz or 1$^\circ$ and smaller, which facilitates, e.g., distant-speech enhancement or source separation.

Recognizing speech under noisy condition is an ill-posed problem. The CHiME 3 challenge targets robust speech recognition in realistic environments such as street, bus, caffee and pedestrian areas. We study variants of beamformers used for pre-processing multi-channel speech recordings. In particular, we investigate three variants of generalized side-lobe canceller (GSC) beamformers, i.e. GSC with sparse blocking matrix (BM), GSC with adaptive BM (ABM), and GSC with minimum variance distortionless response (MVDR) and ABM. Furthermore, we apply several post-filters to further enhance the speech signal. We introduce MaxPower postfilters and deep neural postfilters (DPFs). DPFs outperformed our baseline systems significantly when measuring the overall perceptual score (OPS) and the perceptual evaluation of speech quality (PESQ). In particular DPFs achieved an average relative improvement of 17.54% OPS points and 18.28% in PESQ, when compared to the CHiME 3 baseline. DPFs also achieved the best WER when combined with an ASR engine on simulated development and evaluation data, i.e. 8.98% and 10.82% WER. The proposed MaxPower beamformer achieved the best overall WER on CHiME 3 real development and evaluation data, i.e. 14.23% and 22.12%, respectively.

For automatic speech recognition (ASR) systems it is important that the input signal mainly contains the desired speech signal. For a compact arrangement, differential microphone arrays (DMAs) are a suitable choice as front-end of ASR systems. The limiting factor of DMAs is the white noise gain, which can be treated by the minimum norm solution (MNS). In this paper, we introduce the first time the MNS to adaptive differential microphone arrays. We compare its effect to the conventional implementation when used as front-end of an ASR system. In experiments we show that the proposed algorithms consistently increase the word accuracy up to 50% relative to their conventional implementations. For PESQ we achieve an improvement of up to 0.1 points.

The problem of room localization is to determine where, in a multi-room environment, a person is producing a speech ut-terance. In our work, we are exploiting the information gained from a network of microphones installed all over a house, where the lack of calibration of the microphone energies creates an ad-ditional challenge. This paper compares room localizers based on different features (such as energy and cross-correlation be-tween microphones) and classifiers (such as neural networks and discriminative analysis). In order to evaluate the differ-ent room localizers in terms of word accuracy this paper also presents a complete distant speech recognition system which tries to take advantage of synergy between the different compo-nents without using any oracle information. Finally, the system is analyzed in terms of computational and time resources. Index Terms: Distant speech recognition; microphone net-work; VAD; room localization; machine learning classification; enhancement; reverberant and noisy environment. 1.

The electro-larynx device (EL) offers the possibility to re-obtain speech when the larynx is removed after a total laryngectomy. Speech produced with an EL suffers from inadequate speech sound quality, therefore there is a strong need to enhance EL speech. When disordered speech is applied to Automatic Speech Recognition (ASR) systems, the performance will significantly decrease. ASR systems are increasingly part of daily life and therefore, the word accuracy rate of disordered speech should be reasonably high in order to be able to make ASR technologies accessible for patients suffering from speech disorders. Moreover, ASR is a method to get an objective rating for the intelligibility of disordered speech. In this paper we apply disordered speech, namely speech produced by an EL, on an ASR system which was designed for normal, healthy speech and evaluate its performance with different types of adaptation. Furthermore, we show that two approaches to reduce the directly radiated EL (DREL) noise from the device itself are able to increase the word accuracy rate compared to the unprocessed EL speech.

Determination of pitch marks (PMs) is necessary in clinical voice assessment for the measurement of fundamental frequency (F0) and perturbation. In voice with ambiguous F0, PM determination is crucial, and its validity needs special attention. The study at hand proposes a new approach for PM determination from Laryngeal High-Speed Videos (LHSVs), rather than from the audio signal. In this novel approach, double PMs are extracted from a diplophonic voice sample, in order to account for ambiguous F0s. The LHSVs are spectrally analyzed in order to extract dominant oscillation frequencies of the vocal folds. Unit pulse trains with these frequencies are created as PM trains and compensated for the phase shift. The PMs are compared to Praat's single audio PMs. It is shown that double PMs are needed in order to analyze diplophonic voice, because traditional single PMs do not explain its double-source characteristic.

The Artificial Larynx Transducer (ALT) as a possibility to re-obtain audible speech for people who had to un-dergo a total laryngectomy has been known for decades. Not only the design and underlying technique but also the poor speech quality and intelligibility have not improved until now. In a world where technology rules everyday life, it is necessary to use the known technology to im-prove the quality of life for handicapped people. One reason for the lack of naturalness is the constant vibration of the ALT. A method to substantially improve ALT speech is to introduce a varying fundamental fre-quency (F0)- contour. In this paper we present a new method to automatically learn an artificial F0-contour. The model used is a Gaussian mixture model (GMM) which is trained with a database containing speech of ALT users as well as healthy people. Informal listening tests suggest that this approach is a first step for a sub-sequent overall enhancement technique for speech pro-duced by an ALT. Index Terms: alaryngeal speech, Artificial Larynx Transducer (ALT), fundamental frequency, speech en-

An approach to the recognition of regional language varieties is presented. The algorithm is tested on utterances of 3 to 6 seconds duration taken from large speech databases (SpeechDat) of Austrian and German German. The features are based only on the prosody of the speech and include parameters derived from the Fujisaki model and statistics of the fundamental frequency. Classification is performed using a multilayer perceptron and yields a rate of 64% correct. identification of the regional variety. Those results are then further evaluated for the use of a regional variety recognizer as a front-end of an automatic speech recognizer for different regional varieties. In case there is no a priori information of the distribution of the regional varieties spoken by the users, this approach yields a considerable improvement in the robustness of the speech recognition rates.

In this paper an approach is presented which is aimed to enhance disordered male voices. This approach aims at highpitched voices with a severe degree of hoarseness. The goal of the study is to determine whether pitch modification combined with periodicity enhancement can improve the perceived quality of a disordered speech utterance. Signal manipulation is done pitch-synchronously, so, firstly pitch marks have to be detected. Then period enhancement is performed followed by a PSOLA based pitch modification step. Finally, the period enhancement is performed once more for the utterance with the lower pitch. Perceptual evaluations were performed by both professional speech and language pathologists and naive listeners to rate the subjective perceived enhancement of the voice. Results show that the modified voice has a reduced breathiness, whereas roughness seems not to be influenced by the processing. The most significant result from the naive listener test is a reduced perceived speaking effort.