JFJoachim Fainberg

Joachim Fainberg

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Joachim Fainberg has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview

    by Peter Bell, Joachim Fainberg, Ondrej Klejch, Jinyu Li, Steve Renals, Pawel Swietojanski

    We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.


  • Open Access

    Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview

    by Peter Bell, Joachim Fainberg, Ondrej Klejch, Jinyu Li, Steve Renals, Pawel Swietojanski

    We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.


  • Open Access

    Lattice-based lightly-supervised acoustic model training

    by Joachim Fainberg, Ondřej Klejch, Steve Renals, Peter Bell

    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 supervised training, in which text matching the audio is selected using an existing speech recognition model. Current approaches to light supervision typically filter the data based on matching error rates between the transcriptions and biased decoding hypotheses. In contrast, semi-supervised training does not require matching text data, instead generating a hypothesis using a background language model. State-of-the-art semi-supervised training uses lattice-based supervision with the lattice-free MMI (LF-MMI) objective function. We propose a technique to combine inaccurate transcriptions with the lattices generated for semi-supervised training, thus preserving uncertainty in the lattice where appropriate. We demonstrate that this combined approach reduces the expected error rates over the lattices, and reduces the word error rate (WER) on a broadcast task.

  • Open Access

    Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models

    by Ondrej Klejch, Joachim Fainberg, Peter Bell, Steve Renals

    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 the use of an initial one-best transcription for the test data, generated by an unadapted model, in order to estimate the adaptation transform. It has been found that adaptation methods using discriminative objective functions - such as cross-entropy loss - often require careful regularisation to avoid over-fitting to errors in the one-best transcriptions. In this paper we solve this problem by performing discriminative adaptation using lattices obtained from a first pass decoding, an approach that can be readily integrated into the lattice-free maximum mutual information (LF-MMI) framework. We investigate this approach on three transcription tasks of varying difficulty: TED talks, multi-genre broadcast (MGB) and a low-resource language (Somali). We find that our proposed approach enables many more parameters to be adapted without over-fitting being observed, and is successful even when the initial transcription has a WER in excess of 50%.

  • Open Access

    Learning to adapt: a meta-learning approach for speaker adaptation

    by 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 example by adapting to unseen speakers. The success of speaker adaptation methods relies on selecting weights that are suitable for adaptation and using good adaptation schedules to update these weights in order not to overfit to the adaptation data. In this paper we investigate a principled way of adapting all the weights of the acoustic model using a meta-learning. We show that the meta-learner can learn to perform supervised and unsupervised speaker adaptation and that it outperforms a strong baseline adapting LHUC parameters when adapting a DNN AM with 1.5M parameters. We also report initial experiments on adapting TDNN AMs, where the meta-learner achieves comparable performance with LHUC.