49 citations · 86 across the 12 of their papers we have counts for
13 papers
A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures
Tobias Cord-Landwehr, Christoph Boeddeker, Cătălin Zorilă +2
We introduce a monaural neural speaker embeddings extractor that computes an embedding for each speaker present in a speech mixture. To allow for supervised training, a teacher-stu…
Frame-wise and overlap-robust speaker embeddings for meeting diarization
Tobias Cord-Landwehr, Christoph Boeddeker, Cătălin Zorilă +2
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…
Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition
Mohan Li, Rama Doddipatla, Catalin Zorila
This paper proposes a self-regularised minimum latency training (SR-MLT) method for streaming Transformer-based automatic speech recognition (ASR) systems. In previous works, laten…
Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition
Catalin Zorila, Rama Doddipatla
Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging. Strong speech enhancement front-ends are available, however, they ty…
On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
Jisi Zhang, Catalin Zorila, Rama Doddipatla +1
In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mi…
Transformer-based Streaming ASR with Cumulative Attention
Mohan Li, Shucong Zhang, Catalin Zorila +1
In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monoton…
Monaural source separation: From anechoic to reverberant environments
Tobias Cord-Landwehr, Christoph Boeddeker, Thilo von Neumann +3
Impressive progress in neural network-based single-channel speech source separation has been made in recent years. But those improvements have been mostly reported on anechoic data…
Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
Jisi Zhang, Catalin Zorila, Rama Doddipatla +1
In this paper, we introduce a novel semi-supervised learning framework for end-to-end speech separation. The proposed method first uses mixtures of unseparated sources and the mixt…
Head-synchronous Decoding for Transformer-based Streaming ASR
Mohan Li, Catalin Zorila, Rama Doddipatla
Online Transformer-based automatic speech recognition (ASR) systems have been extensively studied due to the increasing demand for streaming applications. Recently proposed Decoder…
Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
Jisi Zhang, Catalin Zorila, Rama Doddipatla +1
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 environ…
Transformer-based Online Speech Recognition with Decoder-end Adaptive Computation Steps
Mohan Li, Catalin Zorila, Rama Doddipatla
Transformer-based end-to-end (E2E) automatic speech recognition (ASR) systems have recently gained wide popularity, and are shown to outperform E2E models based on recurrent struct…
On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments
Jisi Zhang, Catalin Zorila, Rama Doddipatla +1
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 dire…
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription
Catalin Zorila, Christoph Boeddeker, Rama Doddipatla +1
Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is a…