9 citations · 16 across the 9 of their papers we have counts for
14 papers
Beyond Oversmoothing: Evaluating DDPM and MSE for Scalable Speech Synthesis in ASR
Christoph Minixhofer, Ondrej Klejch, Peter Bell
Synthetically generated speech has rapidly approached human levels of naturalness. However, the paradox remains that ASR systems, when trained on TTS output that is judged as natur…
Speech collage: code-switched audio generation by collaging monolingual corpora
Amir Hussein, Dorsa Zeinali, Ondřej Klejch +6
Designing effective automatic speech recognition (ASR) systems for Code-Switching (CS) often depends on the availability of the transcribed CS resources. To address data scarcity,…
Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling
Ramon Sanabria, Ondrej Klejch, Hao Tang +1
Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KN…
ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition
Yuanchao Li, Zeyu Zhao, Ondrej Klejch +2
In Speech Emotion Recognition (SER), textual data is often used alongside audio signals to address their inherent variability. However, the reliance on human annotated text in most…
The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR
Ramon Sanabria, Nikolay Bogoychev, Nina Markl +3
English is the most widely spoken language in the world, used daily by millions of people as a first or second language in many different contexts. As a result, there are many vari…
Towards Zero-Shot Code-Switched Speech Recognition
Brian Yan, Matthew Wiesner, Ondrej Klejch +2
In this work, we seek to build effective code-switched (CS) automatic speech recognition systems (ASR) under the zero-shot setting where no transcribed CS speech data is available…
Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR
Ondrej Klejch, Electra Wallington, Peter Bell
We present a method for cross-lingual training an ASR system using absolutely no transcribed training data from the target language, and with no phonetic knowledge of the language…
European Language Grid: An Overview
Georg Rehm, Maria Berger, Ela Elsholz +33
With 24 official EU and many additional languages, multilingualism in Europe and an inclusive Digital Single Market can only be enabled through Language Technologies (LTs). Europea…
Speaker Adaptive Training using Model Agnostic Meta-Learning
Ondřej Klejch, Joachim Fainberg, Peter Bell +1
Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-base…
Acoustic Model Adaptation from Raw Waveforms with SincNet
Joachim Fainberg, Ondřej Klejch, Erfan Loweimi +2
Raw waveform acoustic modelling has recently gained interest due to neural networks' ability to learn feature extraction, and the potential for finding better representations for a…
Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models
Ondrej Klejch, Joachim Fainberg, Peter Bell +1
Acoustic model adaptation to unseen test recordings aims to reduce the mismatch between training and testing conditions. Most adaptation schemes for neural network models require t…
Lattice-based lightly-supervised acoustic model training
Joachim Fainberg, Ondřej Klejch, Steve Renals +1
In the broadcast domain there is an abundance of related text data and partial transcriptions, such as closed captions and subtitles. This text data can be used for lightly supervi…
AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection
Joseph Roth, Sourish Chaudhuri, Ondrej Klejch +8
Active speaker detection is an important component in video analysis algorithms for applications such as speaker diarization, video re-targeting for meetings, speech enhancement, a…
Learning to adapt: a meta-learning approach for speaker adaptation
Ondřej Klejch, Joachim Fainberg, Peter Bell
The performance of automatic speech recognition systems can be improved by adapting an acoustic model to compensate for the mismatch between training and testing conditions, for ex…