282 citations · 950 across the 25 of their papers we have counts for
27 papers
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
Albert Zeyer, Ralf Schlüter, Hermann Ney
Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide such an alignment directly and others do not. Connectionist temporal c…
Revisiting the Relation Between Language Model Perplexity and ASR Word Error Rate for Modern End-to-End Speech Recognition
Mohammad Zeineldeen, Albert Zeyer, Haoran Zhang +3
Language model (LM) perplexity (PPL) has historically been used as a proxy for automatic speech recognition (ASR) word error rate (WER), with prior work reporting an approximately…
Text-Utilization for Encoder-dominated Speech Recognition Models
Albert Zeyer, Tim Posielek, Ralf Schlüter +1
This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facilitate faster recognition. We pr…
Diffusion Language Models for Speech Recognition
Davyd Naveriani, Albert Zeyer, Ralf Schlüter +1
Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation.…
LLMs and Speech: Integration vs. Combination
Robin Schmitt, Albert Zeyer, Mohammad Zeineldeen +2
In this work, we study different approaches to utilize large language models (LLMs) for automatic speech recognition (ASR). Specifically, we compare the tight integration of an aco…
Reproducing and Dissecting Denoising Language Models for Speech Recognition
Dorian Koch, Albert Zeyer, Nick Rossenbach +2
Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their abilit…
A Comparative Analysis on ASR System Combination for Attention, CTC, Factored Hybrid, and Transducer Models
Noureldin Bayoumi, Robin Schmitt, Tina Raissi +3
Combination approaches for speech recognition (ASR) systems cover structured sentence-level or word-based merging techniques as well as combination of model scores during beam sear…
Dynamic Acoustic Model Architecture Optimization in Training for ASR
Jingjing Xu, Zijian Yang, Albert Zeyer +3
Architecture design is inherently complex. Existing approaches rely on either handcrafted rules, which demand extensive empirical expertise, or automated methods like neural archit…
The Conformer Encoder May Reverse the Time Dimension
Robin Schmitt, Albert Zeyer, Mohammad Zeineldeen +2
We sometimes observe monotonically decreasing cross-attention weights in our Conformer-based global attention-based encoder-decoder (AED) models, Further investigation shows that t…
Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
Mohammad Zeineldeen, Albert Zeyer, Ralf Schlüter +1
We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks.…
Monotonic segmental attention for automatic speech recognition
Albert Zeyer, Robin Schmitt, Wei Zhou +2
We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, bette…
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…
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…
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…
A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
Mohammad Zeineldeen, Albert Zeyer, Wei Zhou +3
Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units…
A New Training Pipeline for an Improved Neural Transducer
Albert Zeyer, André Merboldt, Ralf Schlüter +1
The RNN transducer is a promising end-to-end model candidate. We compare the original training criterion with the full marginalization over all alignments, to the commonly used max…
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems
Nick Rossenbach, Albert Zeyer, Ralf Schlüter +1
Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recogni…
On using 2D sequence-to-sequence models for speech recognition
Parnia Bahar, Albert Zeyer, Ralf Schlüter +1
Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are…
On Using SpecAugment for End-to-End Speech Translation
Parnia Bahar, Albert Zeyer, Ralf Schlüter +1
This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the…
Language Modeling with Deep Transformers
Kazuki Irie, Albert Zeyer, Ralf Schlüter +1
We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifica…
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation
Christoph Lüscher, Eugen Beck, Kazuki Irie +5
We present state-of-the-art automatic speech recognition (ASR) systems employing a standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder design for th…
RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
Albert Zeyer, Tamer Alkhouli, Hermann Ney
We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder. We sh…