@inproceedings{20504,
  abstract     = {{In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments. In this paper we dissect the gains of the time-domain audio separation network (TasNet) approach by gradually replacing components of an utterance-level permutation invariant training (u-PIT) based separation system in the frequency domain until the TasNet system is reached, thus blending components of frequency domain approaches with those of time domain approaches. Some of the intermediate variants achieve comparable signal-to-distortion ratio (SDR) gains to TasNet, but retain the advantage of frequency domain processing: compatibility with classic signal processing tools such as frequency-domain beamforming and the human interpretability of the masks. Furthermore, we show that the scale invariant signal-to-distortion ratio (si-SDR) criterion used as loss function in TasNet is related to a logarithmic mean square error criterion and that it is this criterion which contributes most reliable to the performance advantage of TasNet. Finally, we critically assess which gains in a noise-free single channel environment generalize to more realistic reverberant conditions.}},
  author       = {{Heitkaemper, Jens and Jakobeit, Darius and Boeddeker, Christoph and Drude, Lukas and Haeb-Umbach, Reinhold}},
  booktitle    = {{ICASSP 2020 Virtual Barcelona Spain}},
  keywords     = {{voice activity detection, speech activity detection, neural network, statistical speech processing}},
  title        = {{{Demystifying TasNet: A Dissecting Approach}}},
  year         = {{2020}},
}

@inproceedings{20505,
  abstract     = {{Speech activity detection (SAD), which often rests on the fact that the noise is "more'' stationary than speech, is particularly challenging in non-stationary environments, because the time variance of the acoustic scene makes it difficult to discriminate  speech from noise. We propose two approaches to SAD, where one is based on statistical signal processing, while the other utilizes neural networks. The former employs sophisticated signal processing to track the noise and speech energies and is meant to support the case for a resource efficient, unsupervised signal processing approach.
The latter introduces a recurrent network layer that operates on short segments of the input speech to do temporal smoothing in the presence of non-stationary noise. The systems are tested on the Fearless Steps challenge database, which consists of the transmission data from the Apollo-11 space mission.
The statistical SAD  achieves comparable detection performance to earlier proposed neural network based SADs, while the neural network based approach leads to a decision cost function of 1.07% on the evaluation set of the 2020 Fearless Steps Challenge, which sets a new state of the art.}},
  author       = {{Heitkaemper, Jens and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}},
  booktitle    = {{INTERSPEECH 2020 Virtual Shanghai China}},
  keywords     = {{voice activity detection, speech activity detection, neural network, statistical speech processing}},
  title        = {{{Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments}}},
  year         = {{2020}},
}

@article{32158,
  abstract     = {{Sociogenesis addresses a pervasive problem in psychology given by Cartesian dualism that assigns the mental an inner locus apart from material activity. Aligning ourselves to the ongoing critical discussions of interiorization in psychology, we explore the crucial notion of space by highlighting language as sociocultural and dialogical activity performed by other-oriented individuals. We discuss space in terms of the “language spacetime”, a symbolic, embodied formation of mutually positioned speaking and listening selves. This leads beyond the “inside-outside” container metaphor and allows for a reformulation of interiorization. Interiorization is conceptualized as a continuous series of different, though mutually related movements between self and other and self and self that lead to and are supported by specific formations in language activity: reversion, transposition, and decoupling. Along a short passage of a video-based interview, we trace the reversion of dialogical positions within the addressivity constellation of the two interlocutors, their interactive creation of a heterotopic spacetime, and the decoupling of one speaker's psychological activity from the concrete here-and-now and the present other by moving and acting into this new sphere. Interiorization appears as a movement at the border of past, present, and possible future(s).}},
  author       = {{Bertau, Marie-Cécile and Karsten, Andrea}},
  issn         = {{0732-118X}},
  journal      = {{New Ideas in Psychology}},
  keywords     = {{Interiorization, Dialogical self, Language activity, Voice, Vygotsky, Heterotopia, Video-confrontation}},
  pages        = {{7--17}},
  publisher    = {{Elsevier BV}},
  title        = {{{Reconsidering interiorization: Self moving across language spacetimes}}},
  doi          = {{10.1016/j.newideapsych.2017.12.001}},
  volume       = {{49}},
  year         = {{2018}},
}

@article{35769,
  abstract     = {{According to the UN Conventions on the Rights of the Child all children have a right to participation. This UN Convention has influenced professionals and policy-makers worldwide. Thereby participation in kindergarten refers to children’s possibilities to exercise influence on a range of topics from the rules that are applied in the nursery’s course of a day, the daily program, the interior design of the facility, etc. Which possibilities for participation children actually have in their everyday lives and how they perceive these possibilities has not been sufficiently answered in the international discourse. Based on a standardized survey with 4 and 5 year old children on their experiences with various aspects of participation in pre-school institutions the paper contributes to international childhood and participation research. The empirical findings are related to the democracy-theoretical inspired figures of early childhood institutions as “nurseries of democracy” and broader reflections on social inequalities in early childhood. }},
  author       = {{Klein, Alexandra and Landhäußer, Sandra}},
  journal      = {{Social Work and Society International Online Journal}},
  keywords     = {{participation, kindergarten, child’s perspectives, voice, inclusion}},
  number       = {{No 2}},
  title        = {{{Children’s Voice in “Nurseries of Democracy“. Participation in Early Childhood Institutions }}},
  doi          = {{https://ejournals.bib.uni-wuppertal.de/index.php/sws/article/view/527}},
  volume       = {{Vol 15}},
  year         = {{2017}},
}

@article{11820,
  abstract     = {{In this paper, we derive an uncertainty decoding rule for automatic speech recognition (ASR), which accounts for both corrupted observations and inter-frame correlation. The conditional independence assumption, prevalent in hidden Markov model-based ASR, is relaxed to obtain a clean speech posterior that is conditioned on the complete observed feature vector sequence. This is a more informative posterior than one conditioned only on the current observation. The novel decoding is used to obtain a transmission-error robust remote ASR system, where the speech capturing unit is connected to the decoder via an error-prone communication network. We show how the clean speech posterior can be computed for communication links being characterized by either bit errors or packet loss. Recognition results are presented for both distributed and network speech recognition, where in the latter case common voice-over-IP codecs are employed.}},
  author       = {{Ion, Valentin and Haeb-Umbach, Reinhold}},
  journal      = {{IEEE Transactions on Audio, Speech, and Language Processing}},
  keywords     = {{automatic speech recognition, bit errors, codecs, communication links, corrupted observations, decoding, distributed speech recognition, error-prone communication network, feature vector sequence, hidden Markov model-based ASR, hidden Markov models, inter-frame correlation, Internet telephony, network speech recognition, packet loss, speech posterior, speech recognition, transmission error robust speech recognition, uncertainty decoding, voice-over-IP codecs}},
  number       = {{5}},
  pages        = {{1047--1060}},
  title        = {{{A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition}}},
  doi          = {{10.1109/TASL.2008.925879}},
  volume       = {{16}},
  year         = {{2008}},
}

@inproceedings{11824,
  abstract     = {{Soft-feature based speech recognition, which is an example of uncertainty decoding, has been proven to be a robust error mitigation method for distributed speech recognition over wireless channels exhibiting bit errors. In this paper we extend this concept to packet-oriented transmissions. The a posteriori probability density function of the lost feature vector, given the closest received neighbours, is computed. In the experiments, the nearest frame repetition, which is shown to be equivalent to the MAP estimate, outperforms the MMSE estimate for long bursts. Taking the variance into account at the speech recognition stage results in superior performance compared to classical schemes using point estimates. A computationally and memory efficient implementation of the proposed packet loss compensation scheme based on table lookup is presented}},
  author       = {{Ion, Valentin and Haeb-Umbach, Reinhold}},
  booktitle    = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)}},
  keywords     = {{distributed speech recognition, least mean squares methods, MAP estimate, maximum likelihood estimation, MMSE estimate, packet loss compensation scheme, packet switched communication, posteriori probability density function, robust error mitigation method, soft-features, speech recognition, table lookup, voice communication, wireless channels}},
  pages        = {{I}},
  title        = {{{An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features}}},
  doi          = {{10.1109/ICASSP.2006.1659984}},
  volume       = {{1}},
  year         = {{2006}},
}