9 accepted papers
We propose a modified teacher-student training for the extraction of frame-wise speaker embeddings that allows for an effective diarization of meeting scenarios containing partially overlapping speech. To this end, a geodesic distance loss is used that enforces the embeddings computed from regions w…
Using a Teacher-Student training approach we developed a speaker embedding extraction system that outputs embeddings at frame rate. Given this high temporal resolution and the fact that the student produces sensible speaker embeddings even for segments with speech overlap, the frame-wise embeddings…
Recent work on enhancement has shown that frequency domain methods may outperform the time domain approaches, while most of the prior art is focused on reporting objective enhancement metrics on simulated noisy data or use less modern hybrid acoustic models for evaluation. In this paper we investiga…
Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging. Strong speech enhancement front-ends are available, however, they typically require that the ASR model is retrained to cope with the processing artifacts. In this paper we explore a speake…
In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunk-wise attention (MoChA) and head-synchronous decoder-end adaptive computation steps (HS-DACS) algorithms, CA tri…
Online Transformer-based automatic speech recognition (ASR) systems have been extensively studied due to the increasing demand for streaming applications. Recently proposed Decoder-end Adaptive Computation Steps (DACS) algorithm for online Transformer ASR was shown to achieve state-of-the-art perfor…
In this paper, we present a novel multi-channel speech extraction system to simultaneously extract multiple clean individual sources from a mixture in noisy and reverberant environments. The proposed method is built on an improved multi-channel time-domain speech separation network which employs spe…
This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to directly separate speech from multiple microphone recordings, with no need of conventional spatial feature extraction. To re…
The CHiME-5 speech separation and recognition challenge was recently shown to pose a difficult task for the current automatic speech recognition systems. Speaker overlap was one of the main difficulties of the challenge. The presence of noise, reverberation and the moving speakers have made the trad…