173 citations · 306 across the 58 of their papers we have counts for
12 papers · 1 filter
Prediction of Listener Perception of Argumentative Speech in a Crowdsourced Dataset Using (Psycho-)Linguistic and Fluency Features
Yu Qiao, Sourabh Zanwar, Rishab Bhattacharyya +4
One of the key communicative competencies is the ability to maintain fluency in monologic speech and the ability to produce sophisticated language to argue a position convincingly.…
Self-Normalized Importance Sampling for Neural Language Modeling
Zijian Yang, Yingbo Gao, Alexander Gerstenberger +3
To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and in…
Conformer-based Hybrid ASR System for Switchboard Dataset
Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher +4
The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on di…
Efficient Sequence Training of Attention Models using Approximative Recombination
Nils-Philipp Wynands, Wilfried Michel, Jan Rosendahl +2
Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word se…
On Language Model Integration for RNN Transducer based Speech Recognition
Wei Zhou, Zuoyun Zheng, Ralf Schlüter +1
The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simp…
Why does CTC result in peaky behavior?
Albert Zeyer, Ralf Schlüter, Hermann Ney
The peaky behavior of CTC models is well known experimentally. However, an understanding about why peaky behavior occurs is missing, and whether this is a good property. We provide…
Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition
Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng +2
Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acou…
Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
Wei Zhou, Albert Zeyer, André Merboldt +2
With the advent of direct models in automatic speech recognition (ASR), the formerly prevalent frame-wise acoustic modeling based on hidden Markov models (HMM) diversified into a n…
Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel +3
Attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions. The integration with an external LM trained on much m…
Librispeech Transducer Model with Internal Language Model Prior Correction
Albert Zeyer, André Merboldt, Wilfried Michel +2
We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is just…
Towards Consistent Hybrid HMM Acoustic Modeling
Tina Raissi, Eugen Beck, Ralf Schlüter +1
High-performance hybrid automatic speech recognition (ASR) systems are often trained with clustered triphone outputs, and thus require a complex training pipeline to generate the c…
A study of latent monotonic attention variants
Albert Zeyer, Ralf Schlüter, Hermann Ney
End-to-end models reach state-of-the-art performance for speech recognition, but global soft attention is not monotonic, which might lead to convergence problems, to instability, t…