https://www.cs.cmu.edu/~illah/PAPERS/socialroboticssurvey.pdf

A survey of socially interactive robots

The environmental robustness of DNN-based acoustic models can be significantly improved by using multi-condition training data. However, as data collection is a costly proposition, simulation of the desired conditions is a frequently adopted strategy. In this paper we detail a data augmentation approach for far-field ASR. We examine the impact of using simulated room impulse responses (RIRs), as real RIRs can be difficult to acquire, and also the effect of adding point-source noises. We find that the performance gap between using simulated and real RIRs can be eliminated when point-source noises are added. Further we show that the trained acoustic models not only perform well in the distant-talking scenario but also provide better results in the close-talking scenario. We evaluate our approach on several LVCSR tasks which can adequately represent both scenarios.

A study on data augmentation of reverberant speech for robust speech recognition

Blind source separation (BSS) for convolutive mixtures can be solved efficiently in the frequency domain, where independent component analysis (ICA) is performed separately in each frequency bin. However, frequency-domain BSS involves a permutation problem: the permutation ambiguity of ICA in each frequency bin should be aligned so that a separated signal in the time-domain contains frequency components of the same source signal. This paper presents a robust and precise method for solving the permutation problem. It is based on two approaches: direction of arrival (DOA) estimation for sources and the interfrequency correlation of signal envelopes. We discuss the advantages and disadvantages of the two approaches, and integrate them to exploit their respective advantages. Furthermore, by utilizing the harmonics of signals, we make the new method robust even for low frequencies where DOA estimation is inaccurate. We also present a new closed-form formula for estimating DOAs from a separation matrix obtained by ICA. Experimental results show that our method provided an almost perfect solution to the permutation problem for a case where two sources were mixed in a room whose reverberation time was 300 ms.

/pdf/a-robust-and-precise-method-for-solving-the-permutation-1drlfzk6ke.pdf

A robust and precise method for solving the permutation problem of frequency-domain blind source separation

The problem of noise reduction has attracted a considerable amount of research attention over the past several decades. Among the numerous techniques that were developed, the optimal Wiener filter can be considered as one of the most fundamental noise reduction approaches, which has been delineated in different forms and adopted in various applications. Although it is not a secret that the Wiener filter may cause some detrimental effects to the speech signal (appreciable or even significant degradation in quality or intelligibility), few efforts have been reported to show the inherent relationship between noise reduction and speech distortion. By defining a speech-distortion index to measure the degree to which the speech signal is deformed and two noise-reduction factors to quantify the amount of noise being attenuated, this paper studies the quantitative performance behavior of the Wiener filter in the context of noise reduction. We show that in the single-channel case the a posteriori signal-to-noise ratio (SNR) (defined after the Wiener filter) is greater than or equal to the a priori SNR (defined before the Wiener filter), indicating that the Wiener filter is always able to achieve noise reduction. However, the amount of noise reduction is in general proportional to the amount of speech degradation. This may seem discouraging as we always expect an algorithm to have maximal noise reduction without much speech distortion. Fortunately, we show that speech distortion can be better managed in three different ways. If we have some a priori knowledge (such as the linear prediction coefficients) of the clean speech signal, this a priori knowledge can be exploited to achieve noise reduction while maintaining a low level of speech distortion. When no a priori knowledge is available, we can still achieve a better control of noise reduction and speech distortion by properly manipulating the Wiener filter, resulting in a suboptimal Wiener filter. In case that we have multiple microphone sensors, the multiple observations of the speech signal can be used to reduce noise with less or even no speech distortion

/pdf/new-insights-into-the-noise-reduction-wiener-filter-5fsg66xg9i.pdf

New insights into the noise reduction Wiener filter

Speech enhancement and separation are core problems in audio signal processing, with commercial applications in devices as diverse as mobile phones, conference call systems, hands-free systems, or hearing aids. In addition, they are crucial preprocessing steps for noise-robust automatic speech and speaker recognition. Many devices now have two to eight microphones. The enhancement and separation capabilities offered by these multichannel interfaces are usually greater than those of single-channel interfaces. Research in speech enhancement and separation has followed two convergent paths, starting with microphone array processing and blind source separation, respectively. These communities are now strongly interrelated and routinely borrow ideas from each other. Yet, a comprehensive overview of the common foundations and the differences between these approaches is lacking at present. In this paper, we propose to fill this gap by analyzing a large number of established and recent techniques according to four transverse axes: 1 the acoustic impulse response model, 2 the spatial filter design criterion, 3 the parameter estimation algorithm, and 4 optional postfiltering. We conclude this overview paper by providing a list of software and data resources and by discussing perspectives and future trends in the field.

/pdf/a-consolidated-perspective-on-multimicrophone-speech-qnbaqxmtvq.pdf

A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation

Information of Loudness in Aural Communication

A Basic Study on the Sound Localization and Separation of Multiple Moving Sources using EM algorithm

難聴者に, 健聴者と同等のラウドネスを与えるように補聴器の利得を決定できる新しいタイプの補聴器が見られるようになってきた。 このような補聴器の特性の決定に当たっては, 難聴者と健聴者のラウドネスが等しくなる音のレベルの関係を表す関数-ラウドネス補償関数-が必要である。 しかし, ある難聴者のラウドネス関数の測定結果から, ラウドネス補償関数を推定する場合には, 健聴者のラウドネス関数のばら付きを考慮する必要がある。 これは, 難聴者が健聴であったとしたときにどのようなラウドネス関数を示すかは知ることができないからである。 そこで本論文では, その難聴者のラウドネス関数の被験者内分散と, 健聴者のラウドネス関数の被験者間分散の和を考慮することにより, ラウドネス補償関数をある幅をもった形で推定することを提案した。 これにより様々なラウドネス感覚を持つ難聴者に対して, 妥当なラウドネス補償関数を推定できることを示した。

https://www.jstage.jst.go.jp/article/audiology1968/39/3/39_3_209/_pdf

Estimation of Loudness Compensation Functions with the Rating Scale Method

In this paper, signal processing techniques which can be applied to automatic speech recognition to improve its robustness are reviewed. The choice of signal processing techniques is strongly dependent on the scenario of the applications. The analysis of scenario and the choice of suitable signal processing techniques are shown through two examples.

Signal Processing Techniques for Robust Speech Recognition

Performance of the echo canceller can be conventionally measured by putting white Gaussian noise into the echo canceller system. However, white Gaussian noise is not adequate as the test signal, since the performance may depend on the characteristics of input test signal, and the characteristics of the white Gaussian noise differ from those of real spoken language. This paper describes characteristics of spoken language required for objective quality evaluation of echo cancellers. Following test signals having various time and frequency characteristics of spoken language are examined: white Gaussian noise, frequency weighted Gaussian noise, artificial voice, composite source signal, and real voice. It is concluded that artificial voice having average characteristics of spoken language in time and frequency domain is satisfied for objective quality evaluation of echo cancellers other than conventional white Gaussian noise, frequency weighted white Gaussian noise, and composite source signal.

Futoshi Asano

Papers

Information of Loudness in Aural Communication

A Basic Study on the Sound Localization and Separation of Multiple Moving Sources using EM algorithm

Estimation of Loudness Compensation Functions with the Rating Scale Method

Signal Processing Techniques for Robust Speech Recognition

Characteristics of spoken language required for objective quality evaluation of echo cancellers.