status: Published

sponsorship: This work was funded by the SB PhD grant of the Research Foundation Flanders (FWO) with project number 1S66217N. (SB PhD grant of the Research Foundation Flanders (FWO)|1S66217N)

Research in deep learning for multi-speaker source separation has received a boost in the last years. However, most studies are restricted to mixtures of a specific number of speakers, called a specific scenario. While some works included experiments for different scenarios, research towards combining data of different scenarios or creating a single model for multiple scenarios have been very rare. In this work it is shown that data of a specific scenario is relevant for solving another scenario. Furthermore, it is concluded that a single model, trained on different scenarios is capable of matching performance of scenario specific models.

With deep learning approaches becoming state-of-the-art in many speech (as well as non-speech) related machine learning tasks, efforts are being taken to delve into the neural networks which are often considered as a black box. In this paper it is analyzed how recurrent neural network (RNNs) cope with temporal dependencies by determining the relevant memory time span in a long short-term memory (LSTM) cell. This is done by leaking the state variable with a controlled lifetime and evaluating the task performance. This technique can be used for any task to estimate the time span the LSTM exploits in that specific scenario. The focus in this paper is on the task of separating speakers from overlapping speech. We discern two effects: A long term effect, probably due to speaker characterization and a short term effect, probably exploiting phone-size formant tracks.

Copyright © 2017 ISCA. Lately there have been novel developments in deep learning towards solving the cocktail party problem. Initial results are very promising and allow for more research in the domain. One technique that has not yet been explored in the neural network approach to this task is speaker adaptation. Intuitively, information on the speakers that we are trying to separate seems fundamentally important for the speaker separation task. However, retrieving this speaker information is challenging since the speaker identities are not known a priori and multiple speakers are simultaneously active. There is thus some sort of chicken and egg problem. To tackle this, source signals and i-vectors are estimated alternately. We show that blind multi-speaker adaptation improves the results of the network and that (in our case) the network is not capable of adequately retrieving this useful speaker information itself.

In this work, we show how to co-train a classifier for active speaker detection using audio-visual data. First, audio Voice Activity Detection (VAD) is used to train a personalized video-based active speaker classifier in a weakly supervised fashion. The video classifier is in turn used to train a voice model for each person. The individual voice models are then used to detect active speakers. There is no manual supervision - audio weakly supervises video classification, and the co-training loop is completed by using the trained video classifier to supervise the training of a personalized audio voice classifier.

Non-negative Matrix Factorization (NMF) has already been applied to learn speaker characterizations from single or non-simultaneous speech for speaker recognition applications. It is also known for its good performance in (blind) source separation for simultaneous speech. This paper explains how NMF can be used to jointly solve the two problems in a multichannel speaker recognizer for simultaneous speech. It is shown how state-of-the-art multichannel NMF for blind source separation can be easily extended to incorporate speaker recognition. Experiments on the CHiME corpus show that this method outperforms the sequential approach of first applying source separation, followed by speaker recognition that uses state-of-the-art i-vector techniques.

Line drawings of 3D environments are often sufficient for scene interpretation. The VLSI implementation of an algorithm for extracting edge information from grey level images is presented. It yields one pixel wide connected edge point strings and is applicable in real-time.>