10 citations · 18 across the 18 of their papers we have counts for
18 papers
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…
Enhancing BEST-RQ Pseudo-Label Quality through Online Refinement for Automatic Speech Recognition
Jingjing Xu, Zijian Yang, Mohammad Zeineldeen +3
BEST-RQ is a simple and effective self-supervised training method for speech representation learning that performs well on automatic speech recognition (ASR) tasks. It generates ps…
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…
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…
Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR
Jintao Jiang, Yingbo Gao, Mohammad Zeineldeen +1
In this paper, alternating weak triphone/BPE alignment supervision is proposed to improve end-to-end model training. Towards this end, triphone and BPE alignments are extracted usi…
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.…
Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Text
Parnia Bahar, Mattia Di Gangi, Nick Rossenbach +1
Automatic Arabic diacritization is useful in many applications, ranging from reading support for language learners to accurate pronunciation predictor for downstream tasks like spe…
Improving Language Model Integration for Neural Machine Translation
Christian Herold, Yingbo Gao, Mohammad Zeineldeen +1
The integration of language models for neural machine translation has been extensively studied in the past. It has been shown that an external language model, trained on additional…
Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss
Mohammad Zeineldeen, Kartik Audhkhasi, Murali Karthick Baskar +1
This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNN-T) models. In hard distillation, a teacher model transcribe…
Analyzing And Improving Neural Speaker Embeddings for ASR
Christoph Lüscher, Jingjing Xu, Mohammad Zeineldeen +2
Neural speaker embeddings encode the speaker's speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, few studies have investigated t…
Enhancing and Adversarial: Improve ASR with Speaker Labels
Wei Zhou, Haotian Wu, Jingjing Xu +4
ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain va…
Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech
Christoph Lüscher, Mohammad Zeineldeen, Zijian Yang +6
Language barriers present a great challenge in our increasingly connected and global world. Especially within the medical domain, e.g. hospital or emergency room, communication dif…
Improving the Training Recipe for a Robust Conformer-based Hybrid Model
Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher +2
Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based o…
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…
Automatic Learning of Subword Dependent Model Scales
Felix Meyer, Wilfried Michel, Mohammad Zeineldeen +2
To improve the performance of state-of-the-art automatic speech recognition systems it is common practice to include external knowledge sources such as language models or prior cor…
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…
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…
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures
Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes +2
Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resourc…